cli-vstash

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references/cli-reference.md explicitly show "vstash add" can ingest arbitrary URLs (e.g., "vstash add https://..."), which are fetched, parsed, and stored and then used by "vstash ask"/"vstash chat" to produce LLM-driven answers, so untrusted public web content can directly influence agent outputs and behavior.