revops
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external context from files such as .agents/product-marketing.md or .claude/product-marketing.md before proceeding with tasks.
- Ingestion points: External markdown files including .agents/product-marketing.md and product-marketing-context.md (referenced in SKILL.md).
- Boundary markers: The skill does not provide specific instructions to use delimiters or ignore potential commands within these ingested files.
- Capability inventory: The skill contains only documentation and templates, with no scripts performing file writes, network requests, or command execution.
- Sanitization: No content sanitization or validation mechanisms are described for the external context ingestion.
Audit Metadata