openspec-explore

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the openspec list --json command to retrieve a list of active changes and project status for awareness of the developer environment.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from repository documentation and codebase files.\n
  • Ingestion points: Reads artifact content from proposal.md, design.md, tasks.md, and various codebase files.\n
  • Boundary markers: Absent; the instructions do not define delimiters or warnings to ignore embedded instructions within processed files.\n
  • Capability inventory: Capabilities include file reading, codebase searching, and executing vendor-specific CLI commands. Implementation of features or writing code is explicitly prohibited by guardrails.\n
  • Sanitization: Absent; no validation or filtering is mentioned for the content retrieved from the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 04:31 PM
Security Audit — agent-trust-hub — openspec-explore