diagnose-ci-failures

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from GitHub, specifically CI logs and pull request metadata. This represents a potential indirect prompt injection surface where malicious instructions could be embedded in build logs to influence the agent. The skill mitigates this risk by explicitly instructing the agent to generate a plan document for human review rather than executing code changes directly.
  • [COMMAND_EXECUTION]: The skill utilizes standard developer tools, git and the GitHub CLI (gh), to perform read-only diagnostic operations. The use of the GH_PAGER environment variable is a documented best practice for scriptable interactions with the GitHub CLI to ensure consistent output formatting.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:59 PM
Security Audit — agent-trust-hub — diagnose-ci-failures