eo-change-review

Pass

Audited by Gen Agent Trust Hub on May 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions are purely text-based and define a workflow for document auditing without involving executable code or scripts.
  • [DATA_EXPOSURE]: Access is restricted to specific project-related files (e.g., change.md, spec.md, .eo-project.json) necessary for the review process. No sensitive system files or credentials are targeted.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it processes untrusted user-created markdown files.
  • Ingestion points: Reads content from change.md and spec.md within the eo-doc/ directory.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or specific safety warnings when processing external text.
  • Capability inventory: Limited to reading local files and writing a markdown report to a fixed relative path (change-review.md).
  • Sanitization: No content validation or sanitization is performed on the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 24, 2026, 04:05 AM
Security Audit — agent-trust-hub — eo-change-review