sf-catalog
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md’s “Before Writing Code” workflow includes multiple web-search and web-fetch steps for Salesforce documentation; if the agent actually fetches and ingests the resulting pages’ readable text at runtime, that is public web content (outsider-authored) entering the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata