pricing
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define an ingestion surface by prompting the agent to read context from external files such as .agents/product-marketing.md. Although this creates a potential for indirect prompt injection if those files are malicious, the risk is negligible as the skill possesses no dangerous capabilities.\n
- Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.\n
- Boundary markers: Absent.\n
- Capability inventory: None; the skill contains no executable scripts or tool definitions.\n
- Sanitization: Absent.\n- [SAFE]: No evidence of prompt injection, obfuscation, remote code execution, or unauthorized file access was found. The skill follows best practices for providing domain-specific context to an agent.
Audit Metadata