work-with-creators-brief-writer
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data when reading a creator's 'best on-brief post' to generate hook angles and style-matching content.
- Ingestion points: Data enters the agent context through the reading of external creator posts as specified in the 'Reads' section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to prevent it from obeying instructions potentially embedded within the creator's content.
- Capability inventory: The skill possesses file-writing capabilities, as it writes output to 'creators//briefs/.md'. It does not explicitly define network or execution capabilities.
- Sanitization: The skill employs a mitigation strategy by requiring all claims to be cleared through the 'claims-gate' skill, ensuring that only verified facts are included in the final output.
Audit Metadata