vale

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

• Third-party content exposure detected (high risk: 0.72). Outsider free text can enter the LLM context via the skill’s runtime ingestion of untrusted user-provided artifacts—e.g., “Vale config”, “target docs”, and “CI/pre-commit contract” (and any logs/evidence the workflow collects)—which are explicitly treated as untrusted input and may contain attacker-controlled prose.