manage-apps-and-sounds-headless

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill both sources login credentials into environment variables and explicitly instructs the tool to "print its API token" via a --reveal option, which requires the agent to output secret values verbatim (high exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill automates logging into a third‑party account, programmatically mints/captures API tokens and uploads content while explicitly advising to clear/bypass proxy/sandbox network controls — behaviors that enable token/credential exfiltration and proxy‑evasion.

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

• Third-party content exposure detected (low risk: 0.10). The workflow drives a headless Playwright login and then submits/queries only parameters supplied by the caller (e.g., CLI args like app/sound names and a local/argument-specified file/URL), with no described runtime ingestion of outsider-authored free text from an attacker-controlled queue/feed or broad web content.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly instructs unsetting proxy environment variables and using curl --noproxy '*' to bypass the sandbox proxy (lines 14-15 and 58), which asks the agent to circumvent a security mechanism and thus poses a moderate-to-high risk to the host environment.