meticulous-cli-record

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt defines a required --apiToken CLI argument and records login flows that capture usernames/passwords/auth tokens, which encourages embedding or outputting secret values verbatim (e.g., in constructed commands or uploads).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill explicitly injects a recorder into users' browsers, captures credentials, auth tokens, and HTTP-only cookies (including via a default CSP bypass for login recordings) and uploads those sessions to an external service—behavior that constitutes deliberate data exfiltration and credential theft.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "record session" and "record login" commands explicitly open a Chromium browser with the Meticulous recorder snippet injected and upload recorded sessions (links shown as https://app.meticulous.ai/...), meaning the skill browses and captures arbitrary third‑party web content that could contain untrusted/user‑generated instructions.