cmd-speckit-analyze

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill accesses local project documentation artifacts such as spec.md, plan.md, and tasks.md. This access is restricted to the intended project scope and is necessary for performing consistency validation.
  • [SAFE]: While the skill includes a remediation step to fix findings, this capability is explicitly gated by a requirement for user confirmation, preventing automated or unauthorized file modifications.
  • [PROMPT_INJECTION]: The skill ingests data from untrusted local markdown files (ingestion points) without using boundary markers or sanitization. This is noted as an indirect prompt injection surface; however, the risk is mitigated because the tool only proposes edits that require manual user review and approval (capability inventory).
  • [SAFE]: No obfuscation, remote code execution, or data exfiltration patterns were detected in the skill instructions. The behavior is consistent with the stated purpose of a documentation analysis tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:41 AM
Security Audit — agent-trust-hub — cmd-speckit-analyze