ai-execute-task

Warn

Audited by Snyk on Jul 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). Outsider-authored free text is ingested via the runtime “Read the PRD, tech spec, tasks, and the specific NN-task.md with the Read tool” path from Obsidian vault files (e.g., engineering/<project>/workplans/<feature>/prd.md, tech-spec.md, tasks.md, and NN-task.md), which are not guaranteed to be authored by the operating user.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 7, 2026, 02:44 PM
Issues
1
Security Audit — snyk — ai-execute-task