anorth-review

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a sophisticated instructional framework for reviewing code changes. It contains no executable scripts, requests no special permissions, and does not use network or filesystem tools. The logic emphasizes human-in-the-loop safety by requiring discussion before applying any suggested edits.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted code diffs and source files, which creates an indirect prompt injection surface. The impact is limited as the skill lacks dangerous capabilities such as shell execution or network access. 1. Ingestion points: Code diffs and source files provided by the environment for review (SKILL.md). 2. Boundary markers: No specific delimiters are defined in the instructions to isolate external code from agent instructions. 3. Capability inventory: Analysis and feedback only; no tools for command execution, file modification, or network exfiltration. 4. Sanitization: No input sanitization or validation of the provided diffs is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 06:48 AM