promo-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from social media promo files which are external to the skill and could theoretically contain instructions designed to bias the AI's review or revision behavior. However, the risk is effectively mitigated by the skill's design, which requires a manual review and approval step from the user before any revisions are written to the file system.\n
- Ingestion points: Reads user-provided Markdown files from the album's promo directory (SKILL.md Step 3).\n
- Boundary markers: Content is clearly delineated by Markdown headings and code blocks (SKILL.md Step 3).\n
- Capability inventory: Has the ability to read and edit project files using standard tools and a vendor-specific MCP.\n
- Sanitization: Relies on user confirmation for every revision step, ensuring that the final content written back to files has been reviewed by a human.
Audit Metadata