offers
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is entirely composed of informational markdown files and standard configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface for untrusted data by instructing the agent to read local context files. While this creates a surface for potential indirect injection, the risk is mitigated by the lack of exploitable capabilities.
- Ingestion points: The agent is directed to read marketing context from
.agents/product-marketing.mdor.claude/product-marketing.md(SKILL.md). - Boundary markers: No specific delimiters or safety instructions are defined for the imported context.
- Capability inventory: No file-writing, network-access, or subprocess-execution capabilities (sinks) were found in the skill's instructions or referenced files.
- Sanitization: Not applicable as there are no dangerous capabilities to protect.
Audit Metadata