product-manager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns such as prompt injection, obfuscation, or data exfiltration were detected. The skill's content matches its stated purpose of providing product management frameworks.
- [NO_CODE] (SAFE): This skill contains no scripts, configuration files, or executable logic. It is composed entirely of natural language instructions and markdown templates.
- [Indirect Prompt Injection] (LOW):
- Ingestion points: Processes user-provided text when creating PRDs, user stories, and roadmaps (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters for user input.
- Capability inventory: None; the skill does not possess capabilities for file writing, network access, or command execution.
- Sanitization: Absent; however, the lack of dangerous tools or code execution triggers renders the risk negligible.
Audit Metadata