project-requirements

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill focuses on documentation generation and does not perform any high-risk operations such as network exfiltration or remote code execution.
  • [PROMPT_INJECTION]: The skill has an inherent surface for indirect prompt injection through user interview responses.
  • Ingestion points: User answers during the requirements gathering phases defined in SKILL.md.
  • Boundary markers: Absent; there are no explicit delimiters to segregate user input from the generation logic.
  • Capability inventory: The skill writes to local files in the docs/project-requirements/ directory.
  • Sanitization: Absent; input is treated as documentation content without validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:39 AM