agentation-self-driving

Warn

Audited by Runlayer on Feb 21, 2026

Risk Level: MEDIUM
Scan Summary
Max Score
78%
Files
2
Flagged
2
Chunks
3
Flagged Files (2)
SKILL.mdHIGH
78.3%

Malicious tool definition detected

Tool: SKILL.md [1/2] Description: --- name: agentation-self-driving description: Autonomous design critique mode using the Agentation annotation toolbar. Use when the user asks to "critique this page," "add design annotations," "review the UI," "self-driving mode," "auto-annotate," or wants an AI agent to autonomously add design feedback annotations to a web page via the browser.

Tool: SKILL.md [2/2] Description: separation, final actions | ## Critique Style 2-3 sentences max per annotation: - **Specific and actionable**: "Stack the install command below the subheading at 16px" not "fix the layout" - **1-2 concrete alternatives**: Reference CSS values, layout patterns, or design systems - **Name the principle**: Visual hierarchy, Gestalt grouping, whitespace, emphasis, conversion design - **Reference comparable products**: "Like how Stripe/Linear/Vercel handles this" Bad

references/two-session-workflow.mdHIGH
78.3%

Malicious tool definition detected

Tool: references/two-session-workflow.md Description: # Two-Session Self-Driving Workflow Full autonomous design review: one agent critiques, another fixes.

Audit Metadata
Max File Score
78%
Classification
UNKNOWN_SERVER
Files Scanned
2
Files Flagged
2
Chunks Analyzed
3
Analyzed
Feb 21, 2026, 10:00 PM
Security Audit — runlayer — agentation-self-driving