kmp-github-issue-governance
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/gh_sub_issue.pyinteracts with the GitHub CLI by executing commands such asgh issue create,gh repo view, andgh api graphqlvia thesubprocess.runmodule. The implementation follows security best practices by passing arguments as a list and not usingshell=Trueto prevent shell injection vulnerabilities. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and transmit markdown payloads from files or standard input to create or update GitHub issues. This ingestion of external data presents a surface for indirect prompt injection, where malicious instructions could be embedded in the processed content. The skill includes a dedicated validation script (
scripts/validate_issue_payload.py) and documentation on shell-safe transport to mitigate accidental or malicious payload corruption. - Ingestion points:
scripts/validate_issue_payload.py(file/stdin) andscripts/gh_sub_issue.py(via--bodyor--body-file). - Boundary markers: The instructions recommend using quoted heredocs (
cat <<'EOF') in shell scripts to isolate markdown payloads and prevent command execution or variable expansion during transport. - Capability inventory: The skill provides automated capabilities to create, list, and update GitHub issues and comments through the
ghCLI. - Sanitization: The
validate_issue_payload.pyscript performs regex-based checks for escaped characters, unclosed code blocks, and unauthorized AI attribution markers.
Audit Metadata