Skills
Navigate
skills/oakoss/agent-skills/github-cli/Gen Agent Trust Hub

github-cli

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documentation describes patterns for reading content from GitHub issues, pull requests, and repository code, which could contain malicious instructions.
  • Ingestion points: Commands like gh issue view (references/issues.md), gh pr status (references/pull-requests.md), and gh search code (references/releases-search.md) ingest external data into the agent's context.
  • Boundary markers: None identified in the skill's reference files or body.
  • Capability inventory: The skill facilitates high-privilege operations including secret management (references/actions.md), arbitrary API execution (references/projects-api.md), and repository modification (references/repos-auth.md).
  • Sanitization: There are no instructions for sanitizing or filtering the retrieved external content before processing.
  • [COMMAND_EXECUTION]: The skill provides patterns for executing arbitrary REST and GraphQL API calls using the gh api and gh api graphql commands (references/projects-api.md).
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of GitHub CLI extensions from remote repositories via gh extension install (references/repos-auth.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:51 AM