Skills
Navigate
skills/jezweb/claude-skills/image-processing/Gen Agent Trust Hub

image-processing

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted filenames and paths that are subsequently used in shell commands and file-write operations.
  • Ingestion points: Image filenames and filesystem paths supplied by the user in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Shell execution via the img-process CLI and filesystem write operations via generated Python scripts using the Pillow library.
  • Sanitization: Absent.
  • [DYNAMIC_EXECUTION]: The skill facilitates the dynamic generation and execution of Python scripts using the Pillow library to perform custom image processing tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:55 PM
Security Audit — agent-trust-hub — image-processing