ai-sorting

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): Analysis of 'SKILL.md' and 'examples.md' reveals no malicious behavior. The files contain Python code snippets and markdown documentation focused on categorizing text such as support tickets and sentiment.
  • [Indirect Prompt Injection] (SAFE): The skill is designed to ingest untrusted data (e.g., messages, reviews) for sorting. This is the primary intended use case. Ingestion points: 'message' in 'SKILL.md' and 'review' in 'examples.md'. Boundary markers: Absent in provided signatures. Capability inventory: No dangerous capabilities like file system access, network requests, or shell execution are present in the code snippets. Sanitization: Not present. Given the lack of dangerous capabilities, this surface is considered safe.
  • [Unverifiable Dependencies] (SAFE): The skill references the 'dspy' package, which is a legitimate library for programming large language models.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM