write-spec

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from existing project files which represents an indirect prompt injection surface.\n
  • Ingestion points: The skill reads docs/PRD.md and features/INDEX.md to establish project context as defined in SKILL.md.\n
  • Boundary markers: Absent. Contents from project documents are treated as authoritative context without delimiters or instructions to ignore potential embedded instructions.\n
  • Capability inventory: Includes file system inspection via git ls-files and file creation or modification within the project repository structure.\n
  • Sanitization: Absent. Data from ingested documentation is directly used to generate feature specifications and update tracking documents without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 07:41 PM
Security Audit — agent-trust-hub — write-spec