skill-vetter
Security-first skill vetting protocol for AI agents. Use before installing any skill from the platform skill market, skillhub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns to determine whether a skill is safe to install.
68
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs the agent to "cat" and read all files from an installed temp directory (via shell_exec), which will expose any embedded API keys, tokens, or passwords to the LLM and could lead to them being reproduced verbatim in reports or outputs.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This workflow reads and cats the downloaded skill files (e.g., `SKILL.md` and `scripts/*.py`) from an outsider-provided installation into the agent’s runtime context via `shell_exec`, which can include free-form prompt-injection content.
- Repository
- dtyq/magic
- Commit
41d7ef4
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.