retro
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from chat logs and repository files to suggest updates to executable artifacts.
- Ingestion points: Chat history, user instructions, repository context, and tool behavior outputs as defined in the 'Inputs to Review' section of SKILL.md.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the data being reviewed.
- Capability inventory: The skill is permitted to use Bash and is explicitly instructed to create or update SKILL.md files, helper scripts, and documentation (as defined in the 'Output' section of SKILL.md).
- Sanitization: Absent. The skill lacks instructions for validating or escaping content extracted from external inputs before using it to generate skill or script updates.
Audit Metadata