keyapi-linkedin

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

• Third-party content exposure detected (high risk: 0.75). High likelihood: scripts/search-keyapi-docs.mjs fetches public KeyAPI docs text at runtime (https://docs.keyapi.ai/llms.txt and linked endpoint pages) and returns extracted OpenAPI fields that the agent will place into its LLM context for routing/execution.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's docs-search helper fetches the external documentation index at https://docs.keyapi.ai/llms.txt at runtime (and may fetch linked docs pages) which directly controls endpoint resolution and thus runtime agent behavior, so this external URL is a required runtime dependency that influences execution.