oss-security-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires preserving exact file paths, line numbers, and code snippets as evidence and explicitly flags hardcoded API keys/tokens, which would force the LLM to reproduce secret values verbatim if found, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires the agent to ingest and analyze untrusted open-source repository contents (e.g., package.json, lockfiles, .github/workflows, source files) as part of Phases 1–4, and those findings directly drive decisions and actions (e.g., "Fail fast", "Safe to Run?" verdicts), so third‑party repo content could indirectly inject instructions that influence the agent's behavior.