github
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
ghbinary to facilitate repository management and interaction. - [EXTERNAL_DOWNLOADS]: The skill metadata references the installation of the GitHub CLI through trusted package managers like Homebrew and APT.
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub (CI logs and API data), which may contain malicious instructions. 1. Ingestion points:
gh run viewandgh apicommands inSKILL.md. 2. Boundary markers: No markers are used to separate external data from system instructions. 3. Capability inventory: Execution ofghCLI commands inSKILL.md. 4. Sanitization: No sanitization or filtering of the GitHub command output is implemented.
Audit Metadata