lov-find-logo
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and parses HTML from external websites to extract logo candidates and metadata. This creates a surface for indirect prompt injection if a site contains malicious instructions in tags like og:image.
- Ingestion points: The scripts/find_logo.py script fetches HTML and image data from external domains provided by the user or derived from brand names.
- Boundary markers: There are no explicit delimiters or instructions for the agent to ignore potentially malicious content within the fetched metadata stored in meta.json.
- Capability inventory: The skill utilizes network access to fetch remote content and file system access to archive logos and metadata in the user's home directory.
- Sanitization: The script extracts URLs and image properties from external HTML without filtering the content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill requires the agent to execute a local Python script (scripts/find_logo.py) to perform its core functionality.
- [EXTERNAL_DOWNLOADS]: The skill fetches configuration and logo assets from external services including Clearbit and Google, and scrapes images from user-specified domains.
Audit Metadata