bdistill-abstract

Warn

Audited by Snyk on Apr 24, 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.md Step 3a "NOVELTY CHECK" and the pipeline steps explicitly require the agent to "search the web" and "Agent: Web search for each candidate (3 query variants)" to ground novelty_score and filter candidates, meaning the agent will fetch and interpret public web content (open third‑party sources) which directly affects decisions in the pipeline.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 24, 2026, 12:06 PM
Issues
1