06-write
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the 'Idea Pool' card (specifically the hook draft, notes, and source fields) and incorporates it into the LinkedIn post generation process. Maliciously crafted text within these fields could potentially override agent instructions during the writing or humanization steps.
- Ingestion points: Data is read from the 'Idea Pool' card as described in the 'What we read' section of SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' warnings for the external data.
- Capability inventory: The skill has the ability to update the 'Idea Pool' card status, create entries in the 'Posts DB', and present generated content to the user.
- Sanitization: There is no explicit mention of validation, escaping, or filtering for the external source content before processing.
Audit Metadata