browse
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md describes runtime browser inspection/fetching commands (e.g.,
browse snapshot,browse get text body,browse cloud fetch) that ingest page/DOM/text content from user-specified URLs or web pages, which are outsider-authored free text, into the agent’s LLM context via the tool outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata