launch
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill instructions are purely advisory and do not contain executable code, network operations, or sensitive data access beyond standard project context files.
- [PROMPT_INJECTION]: The skill is designed to ingest data from local project context files (e.g.,
.agents/product-marketing.md). While this presents a surface for indirect prompt injection if an attacker can modify those files, the skill lacks the capabilities to perform harmful actions, and this ingestion is consistent with the intended use of the agent. - Ingestion points: Reads from
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md. - Boundary markers: None present in the instructions for file reading.
- Capability inventory: None detected; the skill only generates text-based marketing advice.
- Sanitization: No explicit sanitization of input file content is defined.
Audit Metadata