spec-authoring
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of procedural instructions for collaborative specification writing and does not include any scripts, commands, or network operations.
- [NO_CODE]: No executable code, shell commands, or external dependencies were found in the skill files.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests human-provided data during an interview process. 1. Ingestion points: User interaction during the grilling interview phase (SKILL.md). 2. Boundary markers: None identified. 3. Capability inventory: No file-system, network, or code execution capabilities are utilized. 4. Sanitization: None identified.
Audit Metadata