sn-search-image

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script serper_image_search.py using python3. This is the intended primary purpose of the skill and does not involve arbitrary command execution or shell injection risks.
  • [EXTERNAL_DOWNLOADS]: The script performs HTTP POST requests to https://google.serper.dev/images to fetch search results. Serper.dev is a well-known service provider for search APIs.
  • [CREDENTIALS_UNSAFE]: The skill correctly manages sensitive information by requiring the SERPER_API_KEY to be provided via the environment. It does not contain any hardcoded secrets or credentials.
  • [DATA_EXFILTRATION]: While the skill makes network requests, it only sends user-provided search queries to the designated API endpoint and returns the metadata (URLs, titles) of the results. No sensitive local files or user data are accessed or exfiltrated.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:03 AM
Security Audit — agent-trust-hub — sn-search-image