launch
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from local files to gain context for product marketing tasks.
- Ingestion points: The agent is instructed to read from
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdif they exist. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the context files.
- Capability inventory: The skill is strictly informational; it does not utilize tools for command execution, file writing, or network communication.
- Sanitization: The skill does not perform sanitization of the context files, but its limited capabilities mitigate the risk of exploitation.
Audit Metadata