openspec-verify-change

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local codebase and specification files which acts as an attack surface for indirect prompt injection.
  • Ingestion points: In SKILL.md, steps 3, 4, and 5 involve reading file paths returned by the openspec CLI and searching the codebase for implementation evidence.
  • Boundary markers: The instructions do not define delimiters or specific markers to isolate processed file content from the agent's instructions.
  • Capability inventory: The agent uses the openspec CLI to interact with change artifacts and has read access to the local filesystem.
  • Sanitization: There is no explicit sanitization of the content extracted from the codebase or artifact files is mentioned.
  • [COMMAND_EXECUTION]: The skill invokes the openspec CLI to perform its primary function of auditing changes.
  • Evidence: Steps 1, 2, and 3 in SKILL.md detail the execution of openspec list, openspec status, and openspec instructions apply to gather change metadata and artifact locations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 08:20 PM
Security Audit — agent-trust-hub — openspec-verify-change