skills/vansh290802/harness_enginnering_workshop/de-workshop-setup/Snyk

de-workshop-setup

Warn

Audited by Snyk on Oct 20, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (medium risk: 0.30). The skill clones a GitHub repository specified in a configuration file or URL provided by the facilitator, which allows outsider-authored code and text to be ingested into the agent's runtime environment.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute installation scripts fetched via HTTPS from orq.ai, claude.ai, chatgpt.com, and astral.sh, where orq.ai, claude.ai, and chatgpt.com lack established first-party publisher proof in this context, constituting weak/unknown runtime external dependencies.

Issues (2)

W011

MEDIUM

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

W012

MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 20, 2026, 02:49 PM

Issues

2