sapiom-deploy

Warn

Audited by Snyk on Mar 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: 0.90). The skill's orchestrator pattern (references/patterns.md) explicitly calls an external scrape API (https://firecrawl.services.sapiom.ai/v1/scrape) to fetch and parse arbitrary web pages (e.g., data.markdown) and then uses the extracted items to decide and trigger worker tasks, meaning untrusted third-party page content is ingested and can directly influence actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 08:54 AM