churn-prevention
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions (SKILL.md) direct the agent to read product marketing context from local repository files such as .agents/product-marketing.md or .claude/product-marketing.md.
- Ingestion points: External context files are read into the agent's session to provide business background.
- Boundary markers: No delimiting instructions or warnings to ignore embedded commands within the ingested files are provided.
- Capability inventory: The skill is primarily advisory and does not include direct command execution, file system modifications, or network operations, though it references external CLI tools.
- Sanitization: No sanitization or validation of the content within the ingested context files is mentioned.
Audit Metadata