Grades are a hygiene check, not a security guarantee.

Claude Code, Skill

OpenSkill

OpenSkill, a skill listed in the PlugVet directory.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit 9c418d558b1c, unchanged since the check below.

AGENT_IGNORE_INSTRUCTIONS

Why this grade

  • AGENT_IGNORE_INSTRUCTIONS Medium

    Text tells the agent to ignore earlier instructions.

    README.md, line 154 | INJECT | `ignore previous instructions`, prompt injection |

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Pass

    No shell or command execution found, and no extra permission was declared.

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    packages/cli/src/core/hooks.ts, line 120

    // In production: fetch(hook.config.url, { method: 'POST', body: JSON.stringify(payload) })

    README.md, line 153

    | EXFIL | `fetch()`, `process.env`, `eval()`, credential theft |

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_DOTENV

    packages/cli/src/core/analyzer.ts, line 78

    const dangerPatterns = [/eval\s*\(/i, /exec\s*\(/i, /process\.env/i, /fetch\s*\(/i, /rm\s+-rf/i];

    packages/cli/src/core/skill-intelligence.ts, line 84

    /eval\s*\(/i, /process\.env/i, /exec\s*\(/i,

    packages/cli/src/security/scanner.ts, line 29

    { id: 'EXFIL-002', severity: 'critical', pattern: /process\.env|API_KEY|SECRET|TOKEN|PASSWORD/i, desc: 'Secret/env variable access' },

    Show more

    packages/desktop/src/main.js, line 142

    { id: 'EXFIL-002', severity: 'critical', pattern: 'process\\.env', desc: 'Secret access' },

    .gitignore, line 4

    .DS_Store

    .gitignore, line 5

    .env

  • Agent instructions

    Serious

    instructions tell the agent to ignore earlier instructions.

    AGENT_IGNORE_INSTRUCTIONS

    README.md, line 154

    | INJECT | `ignore previous instructions`, prompt injection |

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit 9c418d558b1c. can reach a host that is not written as a fixed address. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.

Date and source

Date checked:

View source

github.com

Commit graded: 9c418d558b1cc6902d07628ada4b29a7ee8a4aad

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen