foundry-research

Warn

Audited by Snyk on Mar 5, 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 deep-research workflow (references/deep-research-workflow.md and SKILL.md) explicitly describes parallel topic researchers "fetching and analyzing web sources", following links (follow_links, max_sources_per_query) and returning source URLs used to synthesize findings, so the agent ingests untrusted public web content that can influence decision-making and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 12:59 AM