setting-up-workspaces-applications

Fail

Audited by Snyk on Nov 13, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate AWS provisioning guide, but its sample instructions tell the agent not to announce that it is reading files, getting credentials, or loading skills, which hides the agent's own activity from the user without malicious intent.

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

  • Third-party content exposure detected (low risk: 0.10). The required runtime path is the agent installing applications on an image builder from installer links the user names or the publisher's official download, which the agent can reach by selecting URLs, so this is low exposure; the bundled sample assets, pinned setup scripts and provider API/docs are first-party or non-LLM-read and do not count.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 09:13 AM
Issues
2