Agent skill · Audited from source
skill-recorder
skill · microsoft/skill-recorderMIT licenceAudited 12 Nov 2026 · source 8a07490b2231
Is it safe? No — BLOCK, grade F (60/100). We read this skill's source at commit 8a07490b2231 and observed filesystem, network and shell access and a hard-coded secret (see the findings). The audit raised 24 findings, 3 critical or high. What it does: Desktop app that records your on-screen work session and uses the GitHub Copilot SDK to reconstruct it as an intent + ordered steps, then builds a reusable Skill or Automation for Microsoft Autopilots like Scout,…
Cite
Cite this page
ModelsAtlas. “skill-recorder (microsoft/skill-recorder)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/microsoft/skill-recorder
Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 3 critical or high findings, starting with “Hard-coded secrets” in evals/sensitive/frames.ts:31. Do not install it without reading them.
Trust audit
Audit 0.4.1 · source read 12 Nov 2026
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
- FilesystemDeclared8 observations
- NetworkDeclared8 observations
- ShellDeclared2 observations
- DependenciesNot pinnedSome versions float
- SecretsFoundSee the findings; values are never shown
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 2 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | FAIL | 19 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 2 |
L3 Inventory | The files and declarations match the source | WARN | 1 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: critical finding, no behavioural pass.
Findings (24)
CRITICALHard-coded secretssecret.github · evals/sensitive/frames.ts:31
{ text: "…", sensitive: true },- Why
- No further detail recorded for this rule.
- Fix
- —
HIGHCode injectioncode.eval_exec · evals/sensitive/ocr-images.ts:228
console.error(`\nSkill Recorder — real-image OCR redaction eval (opt-in, non-hermetic)`);
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · evals/sensitive/ocr-realistic.ts:128
console.error(`\nSkill Recorder — realistic degraded-frame OCR redaction eval (opt-in, non-hermetic)`);
- Why
- evaluates text as code
- Fix
- remove; use a parser or a dispatch table
MEDIUMNetwork egressnet.beacon_words · electron/skillbuilder/instructions.ts:113
side effects, destructive steps, or data exfiltration the user wouldn't expect.
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.aws · evals/sensitive/fixtures/templates.ts:234
{ pre: "…", secret: { value: "…", entityType: "…" } },- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.generic · common/sensitive.test.ts:89
const secret = "…";
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.github · electron/sensitive/frame-heuristics.test.ts:19
const ocr = "…";
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.github · electron/sensitive/frame-heuristics.test.ts:20
assert.ok(caught(ocr, "…"));
- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.github · electron/sensitive/frame-redact.test.ts:36
word("…", 180),- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMHard-coded secretssecret.github · evals/sensitive/fixtures/templates.ts:232
{ pre: "…", secret: { value: "…", entityType: "…" } },- Why
- No further detail recorded for this rule.
- Fix
- —
MEDIUMInventory / provenanceskill.no_skill_md
- Why
- no SKILL.md at the audited path
- Fix
- a skill without its instruction file cannot be reviewed as one
LOWInsecure cryptocrypto.weak_hash · electron/collectors/clipboard.ts:11
return createHash("sha1").update(input).digest("hex").slice(0, 16);- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · electron/architectures/catalogue-provider.ts:11
} from "../../common/architecture-registry";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · electron/architectures/catalogue-registry.test.ts:8
} from "../../common/architecture-registry";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · electron/audio/recorder.ts:15
} from "../../common/audio";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · electron/audio/recorder.ts:21
} from "../../common/ipc";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWFilesystem / pathfs.traversal · electron/audio/recorder.ts:29
} from "../../common/microphone";
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · electron/ai-provider-runtime.test.ts:48
provider: "custom", baseUrl: "https://127.0.0.1:1/v1", model: "gpt-4.1", wireApi: "completions",
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.raw_ip · electron/ai-provider-runtime.test.ts:51
const config = byomRuntimeConfig({ ...profile, baseUrl: `http://127.0.0.1:${address.port}/v1` }, key, dir);- Why
- No further detail recorded for this rule.
- Fix
- —
LOWSupply chainsupply.unpinned · package.json
@github/copilot-sdk, @huggingface/transformers, @secretlint/core, @secretlint/secretlint-rule-pattern, @secretlint/secretlint-rule-preset-recommend, archiver, koffi, react
- Why
- 25 dependency range(s) float
- Fix
- pin exact versions or ship a lockfile
LOWPrompt injectionprompt.credential_read · README.md:115
**Copilot access**, or a supported model provider's API key; the Copilot CLI ships
- Why
- asks the agent to read credentials
- Fix
- —
LOWPrompt injectionprompt.credential_read · README.md:273
> ⚠️ **Please don't capture secrets.** Passwords, access tokens, API keys, credentials, and
- Why
- asks the agent to read credentials
- Fix
- —
INFOInventory / provenanceinv.oversize · docs/images/library.png
docs/images/library.png
- Why
- 1157420 bytes not read
- Fix
- —
INFOInventory / provenanceinv.oversize · src/assets/fonts/Segoe-sans-Italic.woff2
src/assets/fonts/Segoe-sans-Italic.woff2
- Why
- 1271192 bytes not read
- Fix
- —
Audit 0.4.1 · source sha 8a07490b2231 · 12 Nov 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publishermicrosoft GitHub organizationOwner of the repository this skill is read from
- Source foldermicrosoft/skill-recorderThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdict8a07490b2231A 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 ↗We did not capture a SKILL.md for this skill, so there is no instruction text to quote here.
Install
Pinned to the audited commit 8a07490
git clone https://github.com/microsoft/skill-recorder git -C skill-recorder checkout 8a07490b2231
The author documents no install command, so this uses the repository directly. Our verdict covers commit 8a07490b2231 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| GitHub Copilot | Mentioned in its text, not tested | Skills for GitHub Copilot · About GitHub Copilot |
Audit history
Every audit, every source change
- ✕BLOCK F 60 / 100
first audit · source
8a07490b2231
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/microsoft/skill-recorder/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
All automation skills →microsoft/vscode
Update the committed blocks-ci screenshot hashes after the "Screenshots & Tests" check fails, or investigate a screenshot diff reported on a PR. Use when asked to update, accept, or refresh component screenshot…
microsoft/vscode
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports. Covers addDisposableListener, Event.once, MutableDisposable,…
microsoft/vscode
Core principles and workflow router for changes to the Agents Window under src/vs/sessions.
microsoft/vscode
Use when validating Azure DevOps pipeline changes for the VS Code build. Covers queueing builds, checking build status, viewing logs, and iterating on pipeline YAML changes without waiting for full CI runs.
microsoft/vscode
Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This…
microsoft/vscode
Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA…
Add this badge to your README
[](https://modelsatlas.com/skills/microsoft/skill-recorder/)
<a href="https://modelsatlas.com/skills/microsoft/skill-recorder/"><img src="https://modelsatlas.com/skills/microsoft/skill-recorder/badge.svg" alt="ModelsAtlas: BLOCK F"></a>
Questions about skill-recorder
What does the skill-recorder skill do?
Is skill-recorder safe to install?
What can skill-recorder access on my machine?
Which assistants does skill-recorder work with?
How current is this page?
Sources
- github.com/microsoft/skill-recorder — the audited source at commit 8a07490b2231 and every finding aboveObserved · 12 Nov 2026
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.
- What does the skill-recorder skill do?
- Is skill-recorder safe to install?
- What can skill-recorder access on my machine?