pentest-supply-chain

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly queries and analyzes public package registries and artefacts (e.g., npm registry, PyPI, Go proxy) and inspects package metadata and install scripts as part of "Dependency confusion testing" and "Install script and typosquatting analysis" (references/workflows.md), so it ingests untrusted third‑party content the agent must read/interpret.