openspec-propose

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local openspec CLI commands to manage change scaffolds and artifact state. Commands include openspec new change, openspec status, and openspec instructions.
  • [PROMPT_INJECTION]: The skill ingests instructions and project context via the openspec instructions tool output. It includes explicit guardrails to prevent these internal constraints from being reflected in user-facing output files, which acts as a mitigation against indirect injection and data leakage.
  • [EXTERNAL_DOWNLOADS]: The skill identifies a dependency on the openspec CLI but does not attempt to download or install external resources at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:12 AM
Security Audit — agent-trust-hub — openspec-propose