github
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
ghCLI to interact with GitHub, which involves executing shell commands to fetch data and perform repository actions. - [EXTERNAL_DOWNLOADS]: Metadata provides installation instructions for the official GitHub CLI via
brewandapt. As this targets a well-known and official tool, it is documented neutrally. - [PROMPT_INJECTION]: This skill presents an indirect prompt injection surface because it retrieves data from external GitHub sources (e.g., issue titles, PR descriptions, and logs) that could be controlled by malicious actors.
- Ingestion points:
gh api,gh issue list,gh pr checks, andgh run view. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included.
- Capability inventory: Execution of
ghCLI commands which have network access and can modify repository states. - Sanitization: No sanitization or validation of the text content retrieved from GitHub is performed before the agent processes it.
Audit Metadata