pinecone:docs

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow fetches Pinecone documentation pages from https://docs.pinecone.io/... (public web content), which are outsider-authored and may include free-text that the agent reads into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent at runtime to fetch Pinecone documentation and use it to drive responses — for example the fallback URL https://docs.pinecone.io/llms.txt is a runtime-fetched resource whose content would directly control prompts/instructions.