opencli-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples that place plaintext secrets into commands and an eval that reads a card number (e.g., typing "hunter2" and evaling input[name=cardnumber]), which requires the LLM to handle and emit secret values verbatim.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow described by SKILL.md for opencli-browser ingests free text from whatever webpage the agent navigates to via browser state/find/get/extract/network (e.g., rendered DOM text, extracted Markdown, and network response bodies), which can include outsider-authored content on arbitrary user-specified pages.