opencli-repair

Warn

Audited by Snyk on Apr 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to open and inspect live public websites (Step 3 "Explore the Current Website" using commands like "opencli operate open https://example.com/target-page") and to read the diagnostic RepairContext fields (page.url, page.snapshot, networkRequests) so the agent must interpret untrusted, user-generated/third-party page content to decide and perform repairs, which can materially change tool actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 5, 2026, 10:06 AM
Issues
1