app-knowledge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly lists the repository .env file under "Credentials" as a source of knowledge, which requires the agent to read secret values verbatim and therefore risks exposing them in outputs.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly lists "Web automation & browsing: browser-use skill" under sources of knowledge, which indicates the agent will fetch and interpret content from arbitrary public websites (untrusted third‑party content) as part of its workflow and that such content could influence its actions.