review-test-coverage

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were detected. The skill instructions are limited to analytical tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data including code diffs, CI logs, and repository instructions. While this represents a potential ingestion surface for indirect prompt injection, the risk is minimized by explicit instructions to not change system state or perform automated actions based on the review.
  • Ingestion points: Code diffs, CI evidence, and repository files (SKILL.md).
  • Boundary markers: Absent. The instructions do not define specific delimiters for untrusted code content.
  • Capability inventory: The skill restricts its own behavior, forbidding rerunning CI, posting comments, or changing pull-request states.
  • Sanitization: Absent. The skill does not specify escaping or filtering methods for the code it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 03:38 PM
Security Audit — agent-trust-hub — review-test-coverage