caselaw-access-api

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains explicit examples and instructions to include an API token in request headers (e.g., curl -H "Authorization: Token YOUR_API_KEY") which encourages the agent to accept and embed secret values verbatim in generated commands or code.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch full-text opinions from the public Caselaw Access Project API (https://api.case.law/v1/ — e.g., the "full_case" parameter, curl examples, and the search_cases Python sample), so the agent will ingest open/public third‑party content that could materially influence decisions.