research-pipeline

Warn

Audited by Snyk on May 18, 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 explicitly instructs subagents to fetch and open URLs from public sources (see Stage 4 "Fetch-contract" in SKILL.md and the subagent output schema in references/subagent-spec.md) and snapshots those pages via scripts/snapshot_manifest.py (defuddle/firecrawl tiers), so arbitrary third-party web content is read and can influence canonization and downstream decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 18, 2026, 03:44 AM
Issues
1
Security Audit — snyk — research-pipeline