agentation
Visual UI annotation tool for AI agents. Drop the React toolbar into any app — humans click elements and leave feedback, agents receive structured CSS selectors, bounding boxes, and React component trees to find exact code. Supports MCP watch-loop, platform-specific hooks (Claude Code / Codex / Gemini CLI / OpenCode), webhook delivery, and autonomous self-driving critique with agent-browser.
75
63%
Does it follow best practices?
Impact
96%
1.52xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/agentation/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated annotations from the agentation MCP server (e.g., the SKILL.md UserPromptSubmit hook and platform hooks that curl http://localhost:4747/pending and the agentation_watch_annotations watch-loop) and auto-injects that untrusted annotation text into agent prompts/workflows, allowing third-party content to influence agent actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The skill's runtime setup and platform hooks explicitly run npx to fetch-and-execute the agentation-mcp package (e.g., "npx -y agentation-mcp server" — https://www.npmjs.com/package/agentation-mcp), which downloads and executes remote code at runtime and is required for the MCP watch-loop.
- Repository
- supercent-io/skills-template
- Commit
c033769
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.