ui-ux-gtm
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data such as landing page copy, form requirements, and UI descriptions for audits, creating a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: User-provided descriptions of landing pages, signup flows, and dashboard requirements as defined in the 'When to Use' section of
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the analyzed UI content.
- Capability inventory: The agent is provided with
scripts/check-output.pywhich can perform local file read operations. - Sanitization: No sanitization or validation protocols are established for the external content before processing.
- [COMMAND_EXECUTION]: The skill includes an executable script
scripts/check-output.pymeant to be invoked by the agent to verify deliverable structure. The script reads file content from a path provided via command-line arguments to check for the presence of specific markdown headers.
Audit Metadata