product-management
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill is restricted to markdown-based instructions for product management tasks.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: Reads user research (interview notes, surveys), customer feedback, and feature requests as specified in the Inputs section of SKILL.md.
- Boundary markers: Absent. The instructions do not use delimiters or ignore-behavior markers to isolate processed data from the agent's logic.
- Capability inventory: Limited to text generation for artifacts such as PRDs, roadmaps, and feature analyses. The skill does not possess capabilities for file writing, system execution, or network communication.
- Sanitization: Absent. No filtering or validation of user-provided data is defined.
Audit Metadata