ad-copy
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill processes untrusted user data to generate ad copy and has file system write capabilities.
- Ingestion points: User-provided book descriptions and metadata in SKILL.md.
- Boundary markers: None present to distinguish between instructions and user-provided data.
- Capability inventory: Requested
file:writepermission in frontmatter allows writing output to the filesystem. - Sanitization: No sanitization or validation of input data is specified.
- [NO_CODE]: The skill consists entirely of markdown instructions and guidelines; no executable scripts, binaries, or remote code dependencies are included.
Audit Metadata