skills/agentskillexchange/skills/BackstopJS Visual Regression Testing Automation/Gen Agent Trust Hub
BackstopJS Visual Regression Testing Automation
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to automate visual comparisons by visiting external URLs, which creates a potential surface for indirect prompt injection attacks if the web content contains malicious instructions.
- Ingestion points: The skill ingests data from external URLs during screenshot capture.
- Boundary markers: No specific delimiters or boundary markers are defined to isolate untrusted web content.
- Capability inventory: The skill possesses the ability to execute browser automation scripts and local shell commands (
backstop). - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external sources.
- [COMMAND_EXECUTION]: The skill involves the execution of the BackstopJS CLI tool to perform testing tasks.
- Evidence: The documentation describes triggering
backstop referenceandbackstop testruns as part of the primary workflow.
Audit Metadata