keyapi-threads

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

• Third-party content exposure detected (high risk: 0.85). High: the required workflow runs node scripts/search-keyapi-docs.mjs --query ... --resolve, which fetches public docs index text from https://docs.keyapi.ai/llms.txt and then fetches linked endpoint pages, ingesting that outsider-authored free text into the agent context via the script’s JSON output.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches the documentation index at runtime (https://docs.keyapi.ai/llms.txt) and uses the fetched docs pages to determine API methods/paths/parameters that directly control the agent's execution of requests.