skills/sones3/skills/github-triage/Gen Agent Trust Hub

github-triage

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on system-level execution of the gh (GitHub CLI) and git binaries to retrieve repository information and perform issue triage actions.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted external data from GitHub issues and comments.
  • Ingestion points: Untrusted data enters the agent context via gh issue view and comment history (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external issue content as untrusted or to ignore instructions embedded within that data.
  • Capability inventory: The agent can execute gh commands to modify repository state (labels, comments, closing issues) and has the ability to create or modify files in the .out-of-scope/ directory.
  • Sanitization: The instructions do not specify any sanitization or validation of the external content before it is used to generate recommendations or summaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 10:59 AM
Security Audit — agent-trust-hub — github-triage