magic-linguistic-bitext
Warn
Audited by Snyk on Jul 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.72). Step 2/3/4/5 of this skill’s workflow can ingest outsider-authored free text from runtime-fetched public corpora/OPUS/Comparable corpora (e.g., mined sentences from web sources) into the agent’s LLM context for planning/analysis, which is an indirect prompt-injection surface.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata