Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

bmad-editorial-review-prose

skill · bmad-code-org/bmad-methodNOASSERTION licenceAudited 13 Nov 2026 · source 68fa20b6cc9c

★ 55,322pushed today
✕BLOCKGrade F · 55/100 · 22 findings · 68fa20b
55,322repo stars · whole bmad-code-org/bmad-method

Is it safe? No — BLOCK, grade F (55/100). We read this skill's source at commit 68fa20b6cc9c and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 22 findings, 5 critical or high. What it does: Pushes a draft off its first answer with critique methods and proposes one revision. Use when the user or another skill names bmad-advanced-elicitation, or the user says "advanced elicitation". Not for a critique or a…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “bmad-editorial-review-prose (bmad-code-org/bmad-method)”. Retrieved 13 Nov 2026. https://modelsatlas.com/skills/bmad-code-org/bmad-editorial-review-prose

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 5 critical or high findings, starting with “Code injection” in skills/core-tools/bmad/scripts/memlog.py:113. Do not install it without reading them.

Trust audit

Audit 0.4.1 · source read 13 Nov 2026

Trust score55/100✕BLOCK F
0 critical5 high3 medium14 low0 info

BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 129 of 18,389 audited skills.

What the source does

  • FilesystemDeclared5 observations
  • NetworkDeclared3 observations
  • ShellDeclared4 observations
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN4
L1 Static sourceSecrets, path traversal, supply chain, hidden codeFAIL10
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL8
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: instruction override, no behavioural pass.

Findings (22)

HIGHCode injectioncode.deserialize · skills/core-tools/bmad/scripts/memlog.py:113
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
return yaml.load(front, Loader=yaml.BaseLoader) or {}, body
Why
deserialises untrusted bytes into live objects
Fix
use json or yaml.safe_load
HIGHCode injectioncode.deserialize · skills/method/bmad-agent-po/scripts/tickets.py:125
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
data = yaml.load(m.group(1) + "\n", Loader=FrontmatterLoader)
Why
deserialises untrusted bytes into live objects
Fix
use json or yaml.safe_load
HIGHPrompt injectionprompt.hide_from_user · skills/method/bmad-agent-po/references/board.md:71
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
- Query published containers with their leaves; `mirror` reports them under `containers`, never `unmatched`; tell the user when one's tracker status differs from its file's, and close one only through
Why
asks the agent to act without the user's knowledge
Fix
—
HIGHPrompt injectionprompt.hide_from_user · skills/method/bmad-architecture/SKILL.md:25
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
When the stack is open — greenfield, or a small/beginner project that could sit on a paved path — **recommend a well-known current starter** (verify the going choice on the web first): a good one pre-
Why
asks the agent to act without the user's knowledge
Fix
—
HIGHPrompt injectionprompt.override · docs-site/README.md:53
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
The `docs-site/src/content/docs` symlink may not work correctly on Windows without Developer Mode enabled or administrator privileges.
Why
asks the agent to drop prior instructions or safety
Fix
remove the instruction
MEDIUMPrompt injectionprompt.conditional_escalation · skills/method/bmad-code-review/SKILL.md:3
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
description: 'Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code"'
Why
No further detail recorded for this rule.
Fix
—
MEDIUMPrompt injectionprompt.conditional_escalation · skills/method/bmad-retrospective/SKILL.md:3
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
description: 'Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket''s story file and plan, diffs, commits — and produce a retrospective wit
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.hidden_file · .coderabbit.yaml
F-13 Inventory / provenanceCWE-1104Layer L0
.coderabbit.yaml
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · .pre-commit-config.yaml
F-13 Inventory / provenanceCWE-1104Layer L0
.pre-commit-config.yaml
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · .yamllint.yaml
F-13 Inventory / provenanceCWE-1104Layer L0
.yamllint.yaml
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInsecure cryptocrypto.weak_hash · docs-site/src/integrations/diagrams.js:44
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
const hash = createHash('sha1');
Why
No further detail recorded for this rule.
Fix
—
LOWInsecure cryptocrypto.weak_hash · skills/core-tools/bmad-brainstorming/scripts/brain.py:231
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
deg = int(hashlib.md5(cat.encode("utf-8")).hexdigest(), 16) % 360
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · docs-site/scripts/fix-doc-links.js:20
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const DOCS_ROOT = path.resolve(__dirname, '../../docs');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · docs-site/scripts/validate-doc-links.js:21
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const DOCS_ROOT = path.resolve(__dirname, '../../docs');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · docs-site/scripts/validate-sidebar-order.js:18
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const DOCS_ROOT = path.resolve(__dirname, '../../docs');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · docs-site/test/test-rehype-plugins.mjs:396
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const tree = makeAnchorTree('../../../../../../outside.md');
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · docs-site/test/test-rehype-plugins.mjs:398
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
assert(getHref(tree) === '../../../../../../outside.md', 'Target outside content root unchanged', `Got ${getHref(tree)}`);
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · docs-site/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@astrojs/markdown-remark, @astrojs/sitemap, @astrojs/starlight, @eslint/js, astro, eslint, eslint-config-prettier, eslint-plugin-n
Why
13 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWPrompt injectionprompt.authority_framing · skills/method/bmad-agent-pm/assets/template-pitch.md:42
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
<!-- Risks that could blow the appetite, each with how it is patched or avoided. You are now the senior builder looking for what will eat the cycle: unknown technology, an edge case that grows, a depe
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.fetch_and_trust · skills/core-tools/bmod-core-tools/help/help.md:76
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
For a `core-tools` question this document, its topic files, and the installed skills cannot answer, fetch the documentation site at `https://docs.bmad-method.org/` and follow the pages relevant to the
Why
remote text is to be obeyed as instructions
Fix
—
LOWPrompt injectionprompt.fetch_and_trust · skills/method/bmod-method/help/help.md:163
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
For a `method` question this document, its topic files, and the installed skills cannot answer, fetch the documentation site at `https://docs.bmad-method.org/` and follow the pages relevant to the que
Why
remote text is to be obeyed as instructions
Fix
—

Audit 0.4.1 · source sha 68fa20b6cc9c · 13 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherbmad-code-org GitHub organizationOwner of the repository this skill is read from
  • Source folderbmad-code-org/bmad-methodThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict68fa20b6cc9cA new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Pushes a draft off its first answer with critique methods and proposes one revision. Use when the user or another skill names bmad-advanced-elicitation, or the user says "advanced elicitation". Not for a critique or a…

---
name: bmad-advanced-elicitation
description: 'Pushes a draft off its first answer with critique methods and proposes one revision. Use when the user or another skill names bmad-advanced-elicitation, or the user says "advanced elicitation". Not for a critique or a named method such as pre-mortem without that name.'
---

# Advanced Elicitation

A first draft is the most likely draft: centered, agreeable with its own prompt, biased toward adding and toward the first idea. You push it off center in chosen directions through cold readers, and propose a revision the user accepts or rejects. The target is a piece of work in the conversation, whoever wrote it. Work in the surrounding session's language.

## Setup

- Resolve customization: `uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow`; `{workflow.<key>}` below is that table. Script not found means BMad is not set up here: offer the `bmad` skill's setup (`npx skills add bmad-code-org/BMAD-METHOD --skill bmad` first if needed), then run it again. Run `{workflow.activation_steps_prepend}` before anything else and `{workflow.activation_steps_append}` after setup. Read `{workflow.persistent_facts}`: `file:` entries are paths or globs under `{project-root}` to load, the rest are facts as written.
- Resolve config: `uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key core.output_folder --key core.active_initiative`. The session folder is `{workflow.output_dir}/{workflow.output_folder_name}/`, `/{active_initiative}` dropped when unset, `{topic_slug}` a kebab-case name for the target. When the folder already exists, continue the round numbering from the files there and append to its report.
- Catalog calls are `uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow | uv run {skill-root}/scripts/pick_methods.py --customization - --project-root {project-root} <command>`. `list --tier core` is the index, `show <name-or-num>` the row with its form line; a method outside the index still resolves by name through `show`, and `list --all` runs only when the user asks to see everything.

## The Target and the Start

The target is what the user or calling skill points at, at whatever size they name. With no pointer, it is what the last exchange was about, at its own size: the answer, choice or change you just gave, or the one the user just made. A one-line suggestion is a one-line target, not the plan or document around it; the rest of the context informs the pushes but is not pushed. A target that exists only in chat is staged to `target.md` in the session folder; a file target is used in place.

Choose the pushes and start them without waiting:

- Methods named in the call run as named, and a named direction gets its best-fitting method from `list`; say in one line if one is an odd fit for the target, then run it anyway. A call that asks for a surprise draws with `random --tier core --spread`.
- Otherwise `{workflow.default_methods}` run when set. When it is empty, run three pushes, each method from a different direction: the method from `list` that best fits where the target is probably weak, a wildcard from any tier (`list --tier more` adds the rest) chosen as the method whose answer is hardest to predict for this target, and a third push. For a single choice or a target of a few lines, the third is an open push, which asks to push harder and consider alternatives with no method; for a section or document, it is a second method against another weak spot.

One message names the target by path or phrase, says in a line or two where it is probably weak, names each method with its reason, and the round starts. Stop to ask first only when there is no clear target.

## The Brief

Each push gets a brief of exactly these parts and nothing of the conversation beyond them; a calling skill passes them when it invokes you, so use them without re-asking. The author holds every reason for every choice and cannot critique them cold; what a cold reader is not told cannot anchor it.

1. The target: its path, the section if partial, and that its structure (headings, template slots) is a constraint, not content to push. A target of a few lines is quoted in the brief instead.
2. Purpose and consumer, in a line or two.
3. What is settled: the constraints the author worked under, decisions already made, alternatives already rejected, one line each, so the push does not reopen them. Take them from the calling skill's memlog when it keeps one; the memlog itself stays out of the brief.
4. The method: its name, gist and form line from `show`, quoted.
5. The return, sized to the target, a few lines of form and at most five findings for a single choice: the form as the body, then a `## Findings` list, each with location, what is wrong or missing, and the proposed change; only what is specific to this draft, nothing that would be true of any draft of its kind.

Close with: return only that as text, invoke no skill, spawn nothing, edit nothing, read only the files named. A method with several voices (expert panel, stakeholder lens, Delphi) gets one brief per voice so the voices cannot see each other; a voice that should be an installed agent takes its persona from `uv run {project-root}/_bmad/scripts/roster.py --skill {skill-root} --project-root {project-root}`.

## The Round

Run every method push of the round at once, each in its own fresh subagent, all against the same version of the target. An open push is yours: while the readers run, write it from everything the conversation holds, in the same return shape. Save each return as `round-<r>-push-<n>-<method>.md` in the session folder, the open push as `open`.

Without subagents, run at most two pushes yourself, each read fresh from the target file and written in full before you read the other; say so in one line, and offer the brief as a prompt

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 68fa20b

npx skills add bmad-code-org/BMAD-METHOD/skills/core-tools --skill '*'
npx skills add bmad-code-org/BMAD-METHOD/skills/method --skill '*'
npx skills add bmad-code-org/bmad-method-test-architecture-enterprise
uv run /abs/project/_bmad/scripts/render_skill.py \
uv run {project-root}/_bmad/scripts/resolve_customization.py \

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 68fa20b6cc9c only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
WindsurfMentioned in its text, not testedSkills for Windsurf · About Windsurf
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✕BLOCK F 55 / 100

    first audit · source 68fa20b6cc9c

README badge

For maintainers · shows the latest audit

ModelsAtlas: BLOCK FMODELSATLASBLOCK · F
[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/bmad-code-org/bmad-editorial-review-prose/badge.svg)](https://modelsatlas.com/skills/bmad-code-org/bmad-editorial-review-prose/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/bmad-code-org/bmad-editorial-review-prose/badge.svg)](https://modelsatlas.com/skills/bmad-code-org/bmad-editorial-review-prose/)

Questions about bmad-editorial-review-prose

What does the bmad-editorial-review-prose skill do?
Breakthrough Method for Agile Ai Driven Development
Is bmad-editorial-review-prose safe to install?
No — not without reading the findings first. The audit graded it F (55/100) and found 5 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can bmad-editorial-review-prose access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does bmad-editorial-review-prose work with?
Its documentation mentions claude-code, codex, copilot, cursor, gemini-cli, openclaw and windsurf. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (68fa20b6cc9c), read on 2026-11-13. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.