searxng-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's runtime script (scripts/search.py) fetches and parses JSON search results from a user-configured SearxNG instance (base_url obtained via credgoo and used to call {base_url}/search with urllib.request.urlopen), so it ingests untrusted public web/search content that the agent will read and return as part of its workflow (see scripts/search.py and the SKILL.md/install instructions referencing external Searx URLs).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The install scripts run remote code during setup (curl -LsSf https://astral.sh/uv/install.sh | sh and powershell "irm https://astral.sh/uv/install.ps1 | iex") and pip installs requirements from https://skale.dev/credgoo (uv pip install -r https://skale.dev/credgoo), so these URLs are fetched and executed as required dependencies for the skill.