openspec-explore

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the 'openspec list --json' command to retrieve context about active changes. This is a local CLI tool required by the skill and provided by the vendor for project metadata retrieval.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the local codebase and OpenSpec artifacts, creating a surface for indirect prompt injection. Ingestion points: Reads local codebase files and OpenSpec artifacts such as proposal.md and design.md. Boundary markers: Absent. Capability inventory: Restricted to reading files and executing the openspec CLI; code implementation is explicitly forbidden. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 01:18 AM