skills/whytryharder/skills/p-image/Gen Agent Trust Hub

p-image

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation guidelines and documentation hosted on the official GitHub repository for the inference.sh service (raw.githubusercontent.com/inference-sh/). This is a well-known source related to the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied prompts and external image URLs as part of its core functionality.
  • Ingestion points: Prompt and image fields in CLI input strings within SKILL.md.
  • Boundary markers: None provided in examples.
  • Capability inventory: Model execution via the belt CLI.
  • Sanitization: Not specified in the skill definition, presumably handled by the downstream inference service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — p-image