google-maps-api-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user to provide the BrowserAct API key in the chat (and to proceed only once provided), which requires the LLM to receive and likely embed the secret verbatim in requests/commands — an explicit secret-exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The runtime workflow calls BrowserAct’s run-task-by-template and then ingests the returned output.string from get-task (which is derived from Google Maps page content and thus includes outsider-authored free text scraped from the web).

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)