manus

Warn

Audited by Snyk on Mar 21, 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 skill creates Manus tasks and explicitly polls the Manus API for task outputs (SKILL.md "Get Task Status & Output" / "Extracting Output Files") and the included scripts/manus.sh download files from fileUrl returned by the third‑party Manus service (and Manus agents may browse public web), so the agent will ingest untrusted, third‑party content that could contain instructions affecting subsequent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 01:00 PM
Issues
1