issue-coordinator

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of untrusted external data.
  • Ingestion points: The coordinator and worker threads ingest data from GitHub issues, pull requests, project boards, and linked comments (SKILL.md, Preconditions #1 and Worker contract #1).
  • Boundary markers: There are no explicit instructions or delimiters provided to the workers to treat the issue body as data only or to ignore embedded instructions (SKILL.md, Worker prompt).
  • Capability inventory: The worker agents have capabilities to write code, execute tests via /test, run reviews via /review, push to branches, and merge pull requests when authorized.
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from GitHub before it is processed by the Codex worker threads.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 04:22 PM
Security Audit — agent-trust-hub — issue-coordinator