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
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — github