technical-requirements

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from local business requirements documents to generate output.
  • Ingestion points: Reads docs/requirements/brd.md as its primary input source.
  • Boundary markers: None identified in the prompt instructions to isolate data from instructions during the drafting phase.
  • Capability inventory: The skill has permission to write to srs.md and decisions.md and dispatch a sub-agent for review. It does not possess network or shell execution capabilities.
  • Sanitization: No input validation or sanitization is performed on the content of the BRD before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 06:40 AM