openclaw-ghsa-maintainer

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard command-line tools including gh (GitHub CLI), npm, jq, and rg (ripgrep) to perform repository maintenance tasks. These tools are used for their intended purposes within the OpenClaw repository context.
  • [DATA_EXPOSURE]: The skill interacts with the GitHub Security Advisories API. It specifically targets the openclaw/openclaw repository. It includes a security-conscious practice of using mktemp for the npm userconfig flag to avoid reading potentially sensitive local configuration files during version checks.
  • [PROMPT_INJECTION]: The instructions reinforce security protocols, requiring the agent to read SECURITY.md and seek explicit permission before performing sensitive actions like publishing an advisory. No bypass or override patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (GitHub API and npm registry). The risk is mitigated by the use of jq for parsing and constructing JSON payloads, rather than unsafe shell string interpolation, which prevents common injection vulnerabilities during the PATCH process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 02:11 PM
Security Audit — agent-trust-hub — openclaw-ghsa-maintainer