keyapi-twitter

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

• Third-party content exposure detected (high risk: 0.70). High likelihood: the required workflow runs node scripts/search-keyapi-docs.mjs --query ... --resolve, which fetches and parses KeyAPI docs pages at runtime (outsider-authored free text from fetched web content) and then returns extracted endpoint text into the agent’s execution context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's docs-resolver script (scripts/search-keyapi-docs.mjs) fetches the external documentation index https://docs.keyapi.ai/llms.txt (and then may fetch linked pages like https://docs.keyapi.ai/en/twitter/tweet.md) at runtime to extract endpoint methods/paths which directly control what API requests the agent constructs and executes.