buildbot-reviewer

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data, such as issue descriptions and code diffs, which creates a surface for indirect prompt injection where embedded instructions could attempt to influence the review outcome.
  • Ingestion points: Reads task mode, issue content, changed file lists, and diff summaries from the workspace context.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to separate external content from the skill's logic.
  • Capability inventory: The skill uses default agent capabilities to inspect code and tests (file access).
  • Sanitization: There is no explicit sanitization or filtering of the processed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 04:28 AM
Security Audit — agent-trust-hub — buildbot-reviewer