mograph

Fail

Audited by Snyk on Nov 17, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill's visible content is legitimate: its paid-version mention is an openly disclosed, conditional recommendation, and its cover script's runtime asset download and wide local path scanning are disclosed, but they reach beyond what the advertised task needs (fetching remote files and scanning other agents' skill directories without asking), which is sketchy rather than malicious.

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

  • Third-party content exposure detected (low risk: 0.10). The required Step 2 workflow has the agent actively search the web and fetch selected community pages (GitHub READMEs/LICENSEs, blogs, skill directories) for outsider-authored implementation text, and Step 1.5 does the same for images, so the agent must choose what to ingest, which is low risk rather than medium.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill's core step has the agent search the web at runtime and copy community Remotion/HyperFrames code from dynamically selected third-party repositories into src/ to build and render, which is an inbound executable dependency from arbitrary, unverified individual sources, so it is weak/high; the pinned GSAP CDN script and the cover-image downloads from the author's own repository do not change that tier.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill does not ask for sudo, system file edits, user creation, or service/SSH config changes, but it tells the agent to fetch and adapt unvetted community Remotion/HyperFrames code at runtime and run it locally, which is a mild supply-chain risk.

Issues (4)

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).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 17, 2026, 03:29 PM
Issues
4