github-modes

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or data exfiltration attempts were detected in the skill's instructions or examples. All operations leverage the official GitHub CLI tool in a standard manner.
  • [Indirect Prompt Injection] (SAFE): The skill interacts with external content from GitHub (PR descriptions, issue bodies, and file contents) which is a known surface for indirect prompt injection. This is a functional requirement of the integration rather than a vulnerability in the skill itself.
  • Ingestion points: gh pr view, gh issue list, gh api .../contents/ (via SKILL.md).
  • Boundary markers: Absent in provided examples; the agent must implement its own markers when processing results.
  • Capability inventory: The skill allows significant repository interactions including creating PRs, deleting branches, and triggering workflows (via SKILL.md).
  • Sanitization: No explicit sanitization or validation of the ingested external content is defined in the command snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 03:57 PM