ohdear

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent (SKILL.md and references/workflows.md) to activate on ohdear.app URLs and use the ohdear CLI to fetch and parse data (e.g., list-broken-links, get-crawled-urls-details, crawled page/error_message fields and docs URLs), which ingests untrusted, user-generated content from public websites that the agent reads and uses to drive actions and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 11:10 AM
Issues
1