github
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
ghcommand-line utility to interact with GitHub services for repository management. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from data fetched from external sources. Ingestion points: Data is fetched via commands like
gh run view --log-failedandgh issue list, which pull potentially attacker-controlled content (logs, comments, descriptions) into the agent's context. Boundary markers: The instructions do not define clear boundaries or provide warnings to ignore commands embedded in the retrieved data. Capability inventory: The agent has the capability to use theghCLI to interact with GitHub resources. Sanitization: There is no logic for sanitizing or validating the retrieved GitHub content before it is processed by the agent.
Audit Metadata