signup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, shell commands, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill references reading context from external files such as
.agents/product-marketing.md. While this constitutes a data ingestion point, the risk is negligible because the skill lacks any operational capabilities (like tool usage or shell access) that could be misused if those files contained malicious instructions. - Ingestion points:
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md(specified in SKILL.md). - Boundary markers: None identified.
- Capability inventory: No tools, subprocesses, or network operations are defined or requested in the skill files.
- Sanitization: Not applicable.
Audit Metadata