secrets-le-mcp@2.6.3
CAUTION· install onlyPublisher claims: "Enables AI agents to scan code or text content for hardcoded API keys, passwords, tokens, and private keys, reporting each finding by type, confidence, key name, and position. Secret values are never returned, so credentials can be located and addressed without leaving the machine." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
Code inventory arrives with this version's next honeypot run.- It will ask for
- unknown until the next run
- Where it talks to
- unknown until the next run
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Not enough was observed to say yet. Nothing executable in the bundle ran; the trace covers the install step only. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try secrets-le-mcp` runs it now and prints the full answer.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: GitHub token pattern detected; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
const report = scanContent(`${DOCUMENT}`, 'a.env', DEFAULT_OPTIONS);Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<summary><b>Configuring it by hand</b> — any host with an MCP config file</summary> Most hosts read a JSON config. Add one entry: ```json { "mcpServers": { "secFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct./// "key": "ghp_1234567890abcdefghijklmnopqrstuvwxyz----session_id"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.assert.ok(text.includes('.env'), 'results not grouped by file');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.name === '.env' ||Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'**/.env',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.A scan skips dependency folders, files .gitignore leaves out (except .env files) and binary files, unless the secrets-le.workspace.* settings say otherwise.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.name.startsWith('.env.') ||Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tree.write(".gitignore", ".env\n");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tree.write(".gitignore", ".env\n");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."**/.env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// A project keeps its secrets in the .env files its .gitignore leavesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."**/.env.*"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."a clean answer that skipped the .env must say so"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tree.write(".env", "DATABASE_PASSWORD=hunter2hunter2\n");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tree.write(".env", "PASSWORD=hunter2hunter2");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tree.write(".env", "PASSWORD=hunter2hunter2\n");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'**/.env.*',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".netrc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.path.join(workspaceDir, '.env'),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'.netrc',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.name == ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert_eq!(names(&all), [".env"]);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.|| name.starts_with(".env.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.expect(relative(walked.skippedOfNote)).toEqual(['.env', 'server.pem']);Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| `mask.json` | `maskSecretValue` and `maskWithin` over the inputs most likely to drift. |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.* "key": "ghp_1234567890abcdefghijklmnopqrstuvwxyz----session_id"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.(_, i) => `API_KEY_${i}=sk_live_4eC39HqLyjWDarjtT1zdp7d${i}`,Fix: Never read or enumerate credential locations; accept a documented environment variable instead.'.gitignore': '.env\nserver.pem\nnode_modules/\n',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'.env': 'x',Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.await read('nope\n{"jsonrpc":"2.0","id":1,"method":"ping"}\n'),Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim nolindnaidoo: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- GitHub token pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Hidden zero-width characters detected≈ +2 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.