requirements-clarity

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill exhibits a vulnerability surface for indirect prompt injection (Category 8).
  • Ingestion points: Untrusted user requirement descriptions enter the agent context in SKILL.md under 'Step 1: Initial Requirement Analysis'.
  • Boundary markers: Absent; the instructions do not define delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings for either the input processing or the output PRD generation.
  • Capability inventory: The skill has file-write capabilities using the Write tool to save content to ./docs/prds/{feature_name}-v{version}-prd.md.
  • Sanitization: Absent; the skill does not perform escaping, validation, or filtering of the user-provided content before interpolating it into the final document, which could lead to downstream tool or human deception if malicious instructions are embedded in the requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM