vet-skill-idea
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'skill ideas' provided by the user, which are considered untrusted inputs.
- Ingestion points: The [skill idea] argument provided by the user.
- Boundary markers: There are no specific delimiters defined to separate the user's input from the system instructions.
- Capability inventory: The skill itself has model invocation disabled and does not trigger external actions automatically.
- Sanitization: No escaping or filtering is applied to the input content.
- [EXTERNAL_DOWNLOADS]: The instructions suggest the user run a command to download and install external code.
- Evidence: The text recommends running
npx skills add draekien/skills --skill "skill-writing". - The source repository is owned by the author of the skill.
Audit Metadata