jsr-reverse

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires producing and recording "real target request samples" and updating request-chain artifacts (including tokens, cookies, or auth fields) which forces inclusion of credential/token values verbatim in outputs.

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

• Third-party content exposure detected (high risk: 0.90). The skill's intake and workflow explicitly require supplying and capturing arbitrary URLs and page artifacts (see SKILL.md "Intake Contract: URL or target page") and the references direct capturing and reading of external HTML/JS/$_ts scripts and first-/second‑hop responses (e.g., references/rs-collection-and-two-hop-routing.md and request-chain-recording.md), which means the agent will ingest untrusted third-party web content that can influence routing and actions.