video-asset-sources

Fail

Audited by Snyk on Nov 14, 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 licensing guide; its only self-serving element is a disclosed instruction to query varg's own catalog first for unlisted needs, which is promotion of the author's service, so I rate it medium under the recall-first override.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow has the agent actively search and fetch specific clips, tracks and sound effects from community-uploaded libraries (Pexels, Mixkit, Coverr, Freesound, Wikimedia Commons, Internet Archive), so outsider text is consumed only after the agent selects it, which makes this low rather than medium.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The skill's only instructed fetch of remote content that could steer the agent is a curl of an editing playbook from main on an individual's GitHub repo (nateherkai/herk-edit-kit), which is unofficial third-party content, so it is a medium-risk inbound dependency; the other URLs are either data retrieved for assets or study, or come from strong first-party publishers such as varg, HeyGen, Google, Fontsource, Poly Haven, and Simple Icons.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

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
CRITICAL
Analyzed
Nov 14, 2026, 09:49 PM
Issues
3