skills/builderio/agent-native/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes official GitHub API endpoints (api.github.com) and GraphQL for its operations. These are recognized as well-known and trusted services.
  • [CREDENTIALS_UNSAFE]: Authentication is managed through the GITHUB_TOKEN environment variable, which is a standard and secure practice for managing personal access tokens. No hardcoded secrets or credentials were found in the skill instructions.
  • [PROMPT_INJECTION]: The skill processes external data from GitHub (PR bodies, issue comments, and code), creating a surface for indirect prompt injection. While no active exploitation was detected, instructions embedded in external GitHub content could theoretically influence agent behavior.
  • Ingestion points: GitHub PR data, issue details, and code files accessed via functions like getPR and searchPRs.
  • Boundary markers: The skill documentation does not specify the use of delimiters or instructions to ignore embedded commands in the ingested data.
  • Capability inventory: The skill is scoped to read-only operations and GraphQL queries against the GitHub API, lacking capabilities for file system modification or arbitrary shell command execution.
  • Sanitization: There is no mention of explicit sanitization or filtering of content retrieved from GitHub before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:50 AM
Security Audit — agent-trust-hub — github