Agent skill · Audited from source

FDEOps

skill · suboss87/FDEOpsMIT licenceAudited 14 Oct 2026 · source a6e1adaee6d0

★ 962pushed 4 days ago
!CAUTIONGrade B · 86/100 · 24 findings · a6e1ada
962repo stars · whole suboss87/FDEOps

Is it safe? With care — CAUTION, grade B (86/100). We read this skill's source at commit a6e1adaee6d0 and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 24 findings, 0 critical or high. What it does: Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project; distinguish verified facts from inherited claims.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “FDEOps (suboss87/FDEOps)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/suboss87/fdeops

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score86/100!CAUTION B
0 critical0 high3 medium16 low5 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemDeclared8 observations
  • NetworkDeclared3 observations
  • ShellDeclared5 observations
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS7
L1 Static sourceSecrets, path traversal, supply chain, hidden codeWARN13
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS4
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (24)

MEDIUMNetwork egressnet.raw_ip · evals/local-model/check.js:10
F-04 Network egressCWE-200 · CWE-319Layer L1
const endpoint = new URL(process.env.FDEOPS_TEST_OLLAMA || 'http://127.0.0.1:11434')
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.base64_blob · bin/lib/font-css.js:105
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
src: url(data:font/woff2;base64,d09GMgABAAAAAHJoABMAAAABAPAAAHH1AAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGoYFG4GfHhyHTD9IVkFSh1s/TVZBUjwGYD9TVEFUgTgAhRAvfhEICvZo3iMLhEIAMIGoaAE2AiQDiQAEIAWIGgeLSRsb8TXiaSfwQ3YD
Why
No further detail recorded for this rule.
Fix
—
MEDIUMObfuscation / stealthobf.base64_blob · bin/lib/font-css.js:113
F-07 Obfuscation / stealthCWE-506 · CWE-94Layer L1
src: url(data:font/woff2;base64,d09GMgABAAAAAFpEABMAAAAApvwAAFnSAAEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGoItG5AUHIQqP0hWQVKEPj9NVkFSPAZgP1NUQVSBOACFEC9+EQgK8mTbBQuEEgAwgZVSATYCJAOIEAQgBYkGB4hDG7yXNWybVgO7HSDv
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.hidden_file · skills/audit/.fde-generated.json
F-13 Inventory / provenanceCWE-1104Layer L0
.fde-generated.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · skills/board-memo/.fde-generated.json
F-13 Inventory / provenanceCWE-1104Layer L0
.fde-generated.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · skills/brief/.fde-generated.json
F-13 Inventory / provenanceCWE-1104Layer L0
.fde-generated.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · skills/build/.fde-generated.json
F-13 Inventory / provenanceCWE-1104Layer L0
.fde-generated.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · skills/business-case/.fde-generated.json
F-13 Inventory / provenanceCWE-1104Layer L0
.fde-generated.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWFilesystem / pathfs.traversal · .github/scripts/verify-release.cjs:47
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
verifyRelease(require('../../package.json')).then(visible => { process.exitCode = visible ? 0 : 1 })
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · evals/context-budget/check.js:5
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const { boundedSections, recallSections } = require('../../bin/lib/context')
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · evals/delivery/field.js:30
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
fs.cpSync(path.resolve(__dirname, '../../skills', item.skill), path.join(workspace, 'skill'), { recursive: true })
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · evals/delivery/field.js:37
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
fs.copyFileSync(path.resolve(__dirname, '../../package.json'), path.join(runtime, 'package.json'))
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · mcp/fdeops-ingest/server.js:14
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
const masking = require('../../bin/lib/masking').createMasking(
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.beacon_words · test/setup.test.js:32
F-04 Network egressCWE-200 · CWE-319Layer L1
assert.doesNotMatch(f.run(['resume', '--init', 'beacon']).stdout, /run fde setup once/)
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.beacon_words · test/setup.test.js:80
F-04 Network egressCWE-200 · CWE-319Layer L1
assert.equal(f.run(['resume', '--init', 'beacon']).status, 0)
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.beacon_words · test/setup.test.js:87
F-04 Network egressCWE-200 · CWE-319Layer L1
assert.match(f.run(['resume', '--bind']).stdout, /beacon/)
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · docs/verification.md:112
F-04 Network egressCWE-200 · CWE-319Layer L1
FDEOPS_TEST_OLLAMA=http://127.0.0.1:11434 node evals/local-model/check.js qwen3:1.7b
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · test/local-model-runner.test.js:39
F-04 Network egressCWE-200 · CWE-319Layer L1
env: { ...process.env, FDEOPS_TEST_OLLAMA: `http://127.0.0.1:${server.address().port}` },
Why
No further detail recorded for this rule.
Fix
—
LOWPrompt injectionprompt.transfer_instruction · docs/install.md:235
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
The plugin includes all 35 task skills, the `fde` coordinator and session hooks. Invoke `/fdeops:fde` for a project or `/fdeops:integrate` for a task. Plugin namespaces let FDEOps coexist with another
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
INFOInventory / provenanceinv.oversize · media/chat-demo.gif
F-13 Inventory / provenanceCWE-1104Layer L0
media/chat-demo.gif
Why
1645866 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · media/fdeops-skill-map.png
F-13 Inventory / provenanceCWE-1104Layer L0
media/fdeops-skill-map.png
Why
1218472 bytes not read
Fix
—
INFOPrompt injectionprompt.authority_framing · skills/earn-trust/references/earn-trust.md:3
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**Enter when:** new engagement where you don't have full access yet, trust is thin, the customer said "let's start small," or you need to navigate "we don't trust AI-generated code."
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.authority_framing · skills/fde/references/earn-trust.md:3
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**Enter when:** new engagement where you don't have full access yet, trust is thin, the customer said "let's start small," or you need to navigate "we don't trust AI-generated code."
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.credential_read · evals/delivery/field-fixtures/F14/brief.md:3
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
TASK-7 staging validation is blocked by VPN enrollment. A customer approver must grant enrollment; that person and the expected wait are not yet known. The FDE must complete enrollment themselves afte
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha a6e1adaee6d0 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publishersuboss87 GitHub userOwner of the repository this skill is read from
  • Source foldersuboss87/FDEOpsThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicta6e1adaee6d0A new audit runs when the source changes
  • Repository statusNot archivedLast push 4 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project; distinguish verified facts from inherited claims.

---
name: audit
description: Audit an inherited engagement or implementation against its evidence. Use when taking over work or joining mid-project; distinguish verified facts from inherited claims.
---

# audit

<!-- Generated by bin/generate-skills.js; edit the canonical references and catalog. -->

## Purpose

An audit of inherited claims and takeover risks.

Before investigating or acting:
1. Read [the task context contract](references/task-context.md).
2. Read [the method](references/audit.md).

Load further references only when the task needs them. Everything linked is included in this skill; no other skill pack is required.

## Principles

- Work directly from the supplied permitted context. Standalone work does not require an engagement folder or initialization. Record filenames in the method are optional persistence destinations when no engagement is bound.
- If called by @fde, reuse its current sanitized packet and scope. Do not restart setup, discovery or questions already answered.
- The task context contract controls persistence and authority in both modes. Preserve unknowns and distinguish implementation, verification, deployment and acceptance.
- Use the customer's repository instructions and available tools. Report a missing capability or unrun check honestly; do not claim that installing a skill provisions infrastructure.

Excerpt, first 1,360 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 a6e1ada

Download folder ↗
git clone https://github.com/suboss87/fdeops.git
npx skills add suboss87/fdeops --skill fde
npx skills add suboss87/fdeops --skill build

Commands as the repository documents them: shown, never run by us. Our verdict covers commit a6e1adaee6d0 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
Claude DesktopMentioned in its text, not testedSkills for Claude Desktop · About Claude Desktop
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
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 86 / 100

    first audit · source a6e1adaee6d0

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/suboss87/fdeops/badge.svg)](https://modelsatlas.com/skills/suboss87/fdeops/)

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

Similar skills

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/suboss87/fdeops/badge.svg)](https://modelsatlas.com/skills/suboss87/fdeops/)

Questions about FDEOps

What does the FDEOps skill do?
Forward deployed engineering skills for AI coding agents.
Is FDEOps safe to install?
With care. The audit graded it B (86/100) and found 24 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can FDEOps 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 FDEOps work with?
Its documentation mentions claude-code, claude-desktop, codex, copilot, cursor and gemini-cli. 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 (a6e1adaee6d0), read on 2026-10-14. 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.