heyeddi-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runinscripts/_skills_update.pyto call the GitHub CLI (gh). This is used solely for metadata retrieval to check for the latest releases of the skill hub. The implementation follows security best practices by using a specific argument list and settingshell=Falseto prevent command injection. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project documents and opinions that could contain untrusted instructions. It proactively mitigates this risk in
scripts/_untrusted_doc.pyby wrapping processed content in<<<UNTRUSTED_PROJECT_DOC>>>boundary markers and explicitly instructing the agent to treat the content as data only. - [EXTERNAL_DOWNLOADS]: The skill includes functionality to check for updates from the author's official GitHub repository. It does not perform automatic installations; instead, it presents a suggested
npx skills addcommand to the user for manual review and execution, ensuring no remote code is executed without oversight.
Audit Metadata