skills/lovstudio/skills/lov-find-logo/Gen Agent Trust Hub

lov-find-logo

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches brand assets from Clearbit's logo API, Google's favicon service, and official brand URLs requested by the user.\n- [COMMAND_EXECUTION]: Executes the local Python script scripts/find_logo.py to handle networking, image format analysis, and local file storage.\n- [PROMPT_INJECTION]: The skill ingests untrusted HTML content from external websites to extract image metadata, which represents a surface for indirect prompt injection.\n
  • Ingestion points: scripts/find_logo.py (within the scrape_page_images function).\n
  • Boundary markers: None; the script extracts URLs directly from HTML attributes.\n
  • Capability inventory: The script has the ability to perform network requests and write files to the local disk.\n
  • Sanitization: Uses standard library html.parser for extraction; it does not implement specific filtering for instructions in the extracted metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — lov-find-logo