seo-visual
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (mkdir, grep, echo) to manage a local directory structure (.seo-cache) and update the .gitignore file. These are standard maintenance operations. The use of the placeholder {url-slug} in a shell command represents a potential command injection surface if the agent does not sanitize the input before execution.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting and processing external URLs. 1. Ingestion points: URL input parameter used for analysis and screenshot capture. 2. Boundary markers: None identified in the instructions. 3. Capability inventory: Local file system write access (.seo-cache/), shell command execution (mkdir, grep, echo), and file read access to adjacent directories (../seo/, ../seo-audit/). 4. Sanitization: No explicit sanitization or validation of the input URL or the resulting web content is specified.
Audit Metadata