githubbing

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the official GPG signing key and repository configuration from cli.github.com to facilitate the installation of the GitHub CLI via the system package manager.
  • [COMMAND_EXECUTION]: The script scripts/install-gh.sh executes shell commands to modify system repository lists and install software using apt. This is the intended behavior for a tool installation skill.
  • [DATA_EXFILTRATION]: The skill accesses GH_TOKEN or GITHUB_TOKEN environment variables using the configuring helper skill. This is necessary for authenticated operations with the GitHub API via the CLI.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from GitHub (e.g., issue descriptions or PR comments) which may contain instructions targeting the agent.
  • Ingestion points: Output from GitHub CLI commands such as gh issue view or gh pr list.
  • Boundary markers: None present; the skill does not wrap the tool output in specific delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill allows the agent to create issues, view repositories, and perform other authenticated GitHub operations.
  • Sanitization: No explicit sanitization or filtering of remote content is implemented within the provided scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 04:35 AM