github
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFENO_CODECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation and configuration metadata. It does not include any scripts, binaries, or executable code, which significantly reduces the potential attack surface.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the official GitHub CLI (gh). These commands are standard for interacting with GitHub repositories and rely on the user's existing environment and authentication.
- [PROMPT_INJECTION]: The skill interacts with external data that could contain malicious instructions, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through commands like gh pr checks, gh issue list, and gh run view logs, as specified in SKILL.md.
- Boundary markers: There are no specific delimiters or instructions provided to the agent to distinguish between its primary instructions and the content retrieved from GitHub.
- Capability inventory: The agent is empowered to execute shell commands via the gh CLI to perform various repository management tasks.
- Sanitization: The skill does not define any steps to validate, filter, or sanitize the data retrieved from external GitHub sources before it is processed by the agent.
Audit Metadata