pachca-files

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt asks the agent to request a Pachca token from the user and to run commands including that token (via --token or export), which requires the LLM to handle and potentially emit the secret value verbatim in commands — an insecure pattern.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx -y @pachca/cli" which fetches and executes the @pachca/cli package from the npm registry at runtime (https://www.npmjs.com/package/@pachca/cli), so it relies on remote code execution as a required dependency.