playwright-cli
Fail
Audited by Snyk on Aug 11, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill documentation contains explicit examples that embed sensitive values verbatim in CLI commands (e.g., cookie-set abc123, fill "password123") and shows extracting a cookie into a shell variable (TOKEN=$(playwright-cli --raw cookie-get session_id)), which would require the LLM to output or handle secrets directly.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill runtime path reads webpage content/DOM via
playwright-clinavigation (goto/open) and inspection commands likeeval "el => el.textContent" ...,eval ...,snapshot, and trace recording (tracing-start), where the page text could be attacker-controlled when the workflow is pointed at an outsider-authored site.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata