openspec-explore

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from the local codebase and external artifacts, creating a vulnerability surface where the agent could potentially follow instructions embedded in analyzed data.
  • Ingestion points: Reads codebase files and OpenSpec artifacts as specified in artifactPaths within the status JSON.
  • Boundary markers: No explicit delimiters or instructions are used to ensure the agent ignores embedded instructions when reading file content.
  • Capability inventory: The skill has the capability to execute openspec CLI commands and write to project documentation artifacts (proposals, designs, specs).
  • Sanitization: There is no evidence of sanitization or filtering for content read from the codebase before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes the openspec command-line tool to list stores, check change status, and manage project documentation artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 12:13 PM
Security Audit — agent-trust-hub — openspec-explore