browser-replay

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill instructs the agent to load a recorded trajectory and dispatch each step with the recorded args verbatim — those args can include sensitive values (passwords, cookies, API tokens) from the original session, so replay requires the LLM/tooling to handle/output secrets directly.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx to fetch and run remote npm packages at runtime (e.g., "npx -y ruvector@0.2.25 rvf status .rvf" and "npx -y @claude-flow/cli@latest memory search ..."), which executes remote code fetched from the npm registry and is required for the workflow.