devpilot-learn

Warn

Audited by Snyk on May 2, 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). The skill's SKILL.md explicitly instructs the agent to fetch arbitrary web pages using "WebFetch" ("For URLs: Use WebFetch to retrieve the page") and the evals include external article URLs, so the agent ingests untrusted public web content and reads/interprets it to drive summarization and file-generation behavior, enabling indirect prompt-injection risk.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 10:24 AM
Issues
1