managing-product-specifications

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were identified. The skill is purpose-built for documentation tasks and restricts the agent from implementing application code.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it ingests data from repository files (README.md, AGENTS.md, and existing specs) to inform the generation of new documents.
  • Ingestion points: references/creating-prd.md reads README.md and AGENTS.md; references/updating-prd.md reads existing prd.md files.
  • Boundary markers: The skill does not instruct the agent to use specific delimiters or protective instructions when reading these files.
  • Capability inventory: The skill is limited to reading and writing Markdown/Mermaid files. It does not perform network requests or execute arbitrary shell commands.
  • Sanitization: Ingested content is not explicitly sanitized before being placed into templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 11:23 AM
Security Audit — agent-trust-hub — managing-product-specifications