advertising-compliance
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill's purpose involves reviewing untrusted external data (marketing drafts and social media posts), which creates an attack surface for indirect prompt injection. Malicious instructions within these documents could attempt to misuse the agent's requested tools (Bash, Read, Write, Edit).
- Ingestion points: Marketing materials and social media content (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: Bash, Read, Write, and Edit tools are requested.
- Sanitization: No input validation or filtering is specified.
- [NO_CODE]: The skill is purely informational and does not include any accompanying code, scripts, or binary files.
Audit Metadata