diagnosing-ci-and-merge-bottlenecks

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze data from external GitHub sources, which represents an attack surface for indirect prompt injection.
  • Ingestion points: Data fetched via tools mentioned in SKILL.md, including pull-requests (PR titles, labels, author handles), pr-lifecycle (event details), and engineering-analytics-flaky-tests (CI failure evidence).
  • Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags, triple backticks) or explicit "ignore" directives to prevent the agent from following instructions potentially embedded in pull request titles or comments.
  • Capability inventory: The skill is diagnostic in nature; while it reads sensitive pipeline data, it does not include instructions for writing to the filesystem or executing shell commands.
  • Sanitization: There are no guidelines for the agent to sanitize, escape, or validate the content of the data returned by the GitHub API tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:59 PM
Security Audit — agent-trust-hub — diagnosing-ci-and-merge-bottlenecks