postgres-semantic-search

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

• Third-party content exposure detected (high risk: 0.80). The skill's ParadeDB documentation fetch policy (references/paradedb.md) explicitly instructs the agent to fetch and rely on live docs from https://docs.paradedb.com/llms-full.txt, causing the agent to ingest third‑party web content at runtime which can materially influence its subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's ParadeDB Documentation Fetch Policy explicitly instructs fetching and using the live docs at https://docs.paradedb.com/llms-full.txt on first ParadeDB questions in a session, which means remote content is fetched at runtime and directly controls the agent's responses.