content-similarity-checker

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [No Code] (SAFE): The skill consists of documentation and a requirements file but does not include the functional Python scripts (e.g., similarity_checker.py) referenced in the documentation.
  • [Indirect Prompt Injection] (SAFE): The skill's described purpose involves processing untrusted document data for similarity analysis. While this is an attack surface for indirect prompt injection, it is the primary intended function of the tool and no implementation code is present to execute dangerous operations based on this data. Evidence: 1. Ingestion points: compare, compare_files, and compare_folder functions in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Documentation mentions file reporting (generate_report). 4. Sanitization: Not specified in documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:53 PM