pm-tracking-spec-writer
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within its defined scope of generating documentation. It does not perform unauthorized network operations, access sensitive system files, or execute untrusted code.
- [PROMPT_INJECTION]: The skill includes a vulnerability surface for indirect prompt injection because it ingests untrusted user data (such as Product Requirement Documents or core user journeys) and interpolates it directly into an HTML output template. While the instructions do not explicitly mandate sanitization, this is a standard risk for document generation tools and is mitigated by the context-aware nature of the agent. (Ingestion points: User-provided PRD and user description inputs in SKILL.md; Boundary markers: None; Capability inventory: File writing to save HTML documentation; Sanitization: None explicitly defined in the template script).
Audit Metadata