agentation-visual-feedback
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to download and install the 'agentation' package from the npm registry using commands like 'npm install agentation -D'. This package is an external dependency required for the skill's primary functionality.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where an AI agent processes structured data captured from web pages (selectors, text content, and notes), which may contain malicious instructions.
- Ingestion points: Captured UI data (selectors, text) and user-written notes are provided to the agent as input, as described in the 'Working with AI Agents' section.
- Boundary markers: The provided example prompts lack explicit boundary markers or 'ignore embedded instructions' warnings for the injected content.
- Capability inventory: The skill is intended for AI coding agents, which typically have high-privilege capabilities such as file system access and shell command execution.
- Sanitization: The instructions do not specify any sanitization or validation of the captured web content before it is processed by the agent.
Audit Metadata