spec-kit-analyse

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are limited to read-only analysis of local markdown artifacts. No malicious patterns such as prompt injection, persistence, or data exfiltration were detected.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted content from documentation files. 1. Ingestion points: specs/changes//spec.md, plan.md, tasks.md, and FRAMEWORK.md. 2. Boundary markers: None present. 3. Capability inventory: The skill is strictly read-only and lacks capabilities for shell execution, network access, or file-write operations. 4. Sanitization: No sanitization or validation of the ingested content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 04:19 PM