content-reviewer
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to fetch reference documentation (e.g., auditor-runbook.md) from the author's repository on GitHub (aaron-he-zhu/aaron-marketing-skills) if local files are missing. This is a legitimate operation for accessing vendor-controlled configuration and scoring rubrics.
- [PROMPT_INJECTION]: The skill ingests untrusted data from influencer submissions (links, captions, media notes) for analysis. While this presents an indirect prompt injection surface, it is necessary for the skill's primary function and is treated as a low-risk surface. 1. Ingestion points: Influencer content submissions defined in SKILL.md. 2. Boundary markers: None explicitly mentioned for the ingestion part. 3. Capability inventory: Writes review artifacts to memory/audits/influencer/ and memory/hot-cache.md (SKILL.md). 4. Sanitization: None mentioned.
Audit Metadata