product-capability
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in this skill.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as PRDs, roadmap notes, and user discussions to generate technical artifacts. While this represents a data ingestion surface, the skill does not utilize high-risk tools (like network access or arbitrary command execution) that could be exploited via malicious data.
- Ingestion points: Reads product intent from issues, discussions, and external PRDs.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill performs text analysis and generates/updates documentation files (e.g.,
PRODUCT.md). No network or dynamic execution capabilities are present. - Sanitization: No explicit sanitization of input data is mentioned, but the output is intended for human-in-the-loop review as a capability plan.
Audit Metadata