openspec-reflect

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run git status and git diff --stat for calculating scope deviation. It also references project-specific commands like openspec show and openspec status as noted in reference.md. These actions are standard for development workflows and consistent with the skill's purpose.\n- [PROMPT_INJECTION]: The skill processes untrusted project documentation, which creates a surface for indirect prompt injection.\n
  • Ingestion points: Reads content from proposal.md, tasks.md, and specs/*.md (defined in SKILL.md).\n
  • Boundary markers: No explicit delimiters or instruction-ignoring warnings are used when processing file content.\n
  • Capability inventory: The skill has access to Edit for file modifications and Bash for command execution.\n
  • Sanitization: No validation or filtering of external content is documented prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:18 AM
Security Audit — agent-trust-hub — openspec-reflect