spec-writing

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is an instructional resource for creating project specifications and does not contain executable code or perform sensitive operations.
  • [PROMPT_INJECTION]: The skill establishes a specification format used to drive agent actions, representing an indirect prompt injection surface for data processed at runtime. Evidence: 1. Ingestion points: .claude/sprint/[N]/specs.md. 2. Boundary markers: Absent for specification content. 3. Capability inventory: Code implementation and testing. 4. Sanitization: Absent.
  • [SAFE]: External references to technologies such as PostgreSQL and Socket.io are provided as illustrative examples within documentation and do not constitute external downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 08:58 AM