openspec-apply-change

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the openspec CLI tool to perform actions like listing changes, checking status, and retrieving implementation instructions. The shell commands use properly quoted variables (e.g., "<name>") to minimize the risk of command injection.
  • [DATA_EXFILTRATION]: The skill reads project-specific context files identified by the CLI tool. This access is limited to the files necessary for implementing requested features and does not target sensitive system directories such as .ssh or .aws credentials.
  • [PROMPT_INJECTION]: The instructions include clear guardrails that prevent the agent from proceeding with ambiguous tasks. It explicitly directs the agent to pause and ask for user clarification rather than making assumptions, which helps mitigate risks from malformed or malicious task descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 12:05 PM
Security Audit — agent-trust-hub — openspec-apply-change