seo-visual
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external URLs, creating a surface where instructions embedded in the target webpage could influence agent behavior.
- Ingestion points: Processes a user-provided URL for visual auditing and screenshot capture.
- Boundary markers: There are no explicit delimiters or instructions defined to isolate the content retrieved from the URL from the agent's core logic.
- Capability inventory: The skill uses visual analysis tools and performs file system operations (writing results to a cache directory).
- Sanitization: No content sanitization or validation of the remote page content is described.
- [COMMAND_EXECUTION]: The skill provides shell commands for basic project configuration and directory management.
- Evidence: Provides mkdir commands for directory setup and grep/echo commands to update the .gitignore file to exclude the cache directory. These are standard project hygiene tasks.
Audit Metadata