photo-clipper

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it interpolates user-provided text directly into a template sent to an LLM in references/implementation.md.
  • Ingestion points: The prompt variable in the analyze_photo function.
  • Boundary markers: Absent; the user prompt is concatenated directly into the template.
  • Capability inventory: Image cropping (PIL), file writing (PIL), and network requests (requests).
  • Sanitization: Present; the validate_crop_suggestion function strictly validates the LLM's output against percentage ranges (0-100) and enforces a 50% maximum removal limit per dimension.
  • [DATA_EXFILTRATION] (LOW): The skill transmits image data and an API key to openrouter.ai. While this is required for its functionality, it is a non-whitelisted domain and involves data transit to a third-party service.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM