paid-ads
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to load content from '.agents/product-marketing-context.md'.
- Ingestion points: External file '.agents/product-marketing-context.md' is referenced in SKILL.md.
- Boundary markers: No explicit markers or delimiters are defined for the loaded content.
- Capability inventory: The skill is limited to text-based campaign planning and does not possess capabilities for file writing, network requests, or command execution.
- Sanitization: No validation or sanitization is performed on the ingested file. The overall risk is safe as the skill lacks exploitable capabilities.
Audit Metadata