Skills
skills/devskale/skale-skills/searxng-search/Gen Agent Trust Hub

searxng-search

Fail

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The installation scripts (install.sh, install.bat) download and execute the uv package manager installer from astral.sh using piped shell commands (curl | sh and powershell | iex). This originates from a well-known technology provider.\n- [EXTERNAL_DOWNLOADS]: The skill fetches the credgoo dependency configuration from the vendor's infrastructure at skale.dev during the installation process.\n- [COMMAND_EXECUTION]: On Windows, the setup script uses powershell -ExecutionPolicy ByPass to enable the installation of the uv tool in the local environment.\n- [PROMPT_INJECTION]: The skill processes untrusted external data from search results, which is a surface for indirect prompt injection.\n
  • Ingestion points: Results from SearXNG (titles and snippets) in scripts/search.py are printed to the terminal.\n
  • Boundary markers: Absent; search content is displayed without specific delimiters or instructions for the agent to ignore embedded commands.\n
  • Capability inventory: The skill has the ability to make network requests and access stored credentials through the vendor-provided credgoo utility.\n
  • Sanitization: Content is not sanitized or filtered before it is presented to the agent.
Recommendations
  • HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 2, 2026, 02:43 AM