universal-api-glue

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly directs the agent to generate authentication and request logic and to persistently add new tools without specifying secure handling (e.g., using env vars or CLI auth), so it very likely will ask for, process, or embed API keys/tokens and could output them verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Scrape the documentation of any target API (even if undocumented, use reverse-engineering logic)," meaning it will fetch and ingest open/public third-party API docs and related web content and then use that content to generate auth/request logic and permanently add tools—allowing untrusted external content to directly influence agent behavior.