memory-documentary

Warn

Audited by Snyk on Apr 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The execution protocol (references/execution-protocol.md, Phase 3 "GitHub Issues") explicitly instructs the agent to run gh issue list and ingest issue bodies/comments/quotes (user-generated, public GitHub content) as primary evidence that will be read, synthesized, and used to drive findings and recommendations, so untrusted third-party content can influence tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 26, 2026, 03:46 PM
Issues
1