tentpole-campaign
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files such as
.agents/marketing-learnings.mdand.agents/marketing-strategy.mdto inform campaign planning.\n - Ingestion points: Reads campaign context and past learnings from local markdown files in the
.agents/directory (SKILL.md).\n - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions that might be embedded in these strategy files.\n
- Capability inventory: The skill is purely instructional and does not contain any code execution, file writing, or network operations.\n
- Sanitization: There is no mention of sanitizing or validating the content read from these files before using it in the prompt.\n- [NO_CODE]: The skill consists entirely of markdown instructions and evaluation data without any executable scripts (Python, JavaScript, etc.).
Audit Metadata