github
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for using the
ghCLI to perform actions such as checking pull request status, listing workflow runs, and querying the GitHub API. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from external GitHub resources, creating a potential vector for indirect prompt injection.
- Ingestion points: Commands like
gh run view --log-failed,gh pr checks, andgh apiretrieve external data including workflow logs, pull request details, and issue comments. - Boundary markers: There are no instructions to use delimiters or specific markers to separate external content from the agent's core instructions.
- Capability inventory: The agent is empowered to execute shell commands via the
ghtool and process the resulting output. - Sanitization: No procedures are provided to validate or sanitize the retrieved GitHub content before the agent acts upon it.
Audit Metadata