The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill processes untrusted external data from the web, which could contain hidden instructions designed to manipulate the agent's output or behavior.
Ingestion points: SKILL.md (Step 1 and Step 3 use fetch_url to ingest content from docs.langchain.com).
Boundary markers: Absent; the instructions do not provide delimiters or warnings to ignore instructions found within the retrieved documentation.
Capability inventory: The skill uses retrieved content to provide guidance and complete user requests, potentially allowing data to influence logic.
Sanitization: Absent; there is no validation or filtering of the content fetched from the remote documentation URLs.
[External Downloads] (SAFE): The skill references docs.langchain.com for documentation. This is a reputable source associated with the langchain-ai ecosystem, which is recognized as a trusted entity. The operation is limited to data retrieval with no evidence of sensitive data transmission.

langgraph-docs