wiki-ingest
Warn
Audited by Snyk on Jul 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: 0.78). SKILL.md:13-28 describes fetching outsider-authored web content via
web_fetch/skillwiki ingest <staged-paste-path>(for URL or staged paste file) so the fetched/pasted prose is read by the skill at runtime and then used to generate and publish pages, creating an indirect prompt-injection path into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata