code-security-scanner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to locate .env/config files and include "offending code snippets" (e.g., hardcoded API keys, tokens, or secrets) in the generated report, which would require outputting secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to query and interpret public npm registry data and package metadata (e.g., "For each dep: npm view time --json", "check npm registry", and "npm audit --json" in references/dependency-risks.md), which are untrusted, user-published third‑party sources and whose contents are used to drive scan decisions.