prompt-engineering

Warn

Audited by Snyk on Mar 31, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly defines and instructs use of a web_search tool in the / "Tool Usage Guidance" and "Tool Selection Criteria" sections (e.g., web_search(query: str) -> list[dict] and guidance like "When to use: Need latest framework docs"), and it lists external links in "Related Resources", meaning the agent is expected to fetch and interpret public third-party web content that could influence decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 09:09 AM
Issues
1
Security Audit — snyk — prompt-engineering