tech-article-writer
Warn
Audited by Snyk on Feb 27, 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 tells the agent (under "使用技巧") to use WebSearch and to "collect real cases from GitHub, Stack Overflow" — public, user-generated sources the agent is expected to ingest to inform its writing, which can materially influence its outputs and enable indirect prompt injection.
Audit Metadata