ux-audit
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONPRIVILEGE_ESCALATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data (scenarios, foundation, source code) to perform audits. This presents a surface for indirect prompt injection where malicious instructions embedded in these files could influence agent behavior during the auditing process.
- Ingestion points: The skill reads project documentation (
docs/ux/scenarios.md,docs/ux/foundation.md,docs/brand/voice.md) and the full project source code to verify implementation against requirements. - Boundary markers: Absent; the analyzed content is not wrapped in specific delimiters or preceded by instructions for the agent to ignore embedded commands.
- Capability inventory: The skill can execute shell commands (
python3,npx), read and write project files, and interact with the Figma Plugin API. - Sanitization: No explicit sanitization or filtering of the audited content is performed before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill involves the execution of local scripts and vendor-provided CLI tools to perform automated checks.
- Executes
python3 docs/ux/lint.pyandpython3 docs/brand/lint.pyfrom the local project directory to detect structural drift. - Executes
npx sheleg-design-skill --lint <dir>to verify visual style compliance against a design system. - [PRIVILEGE_ESCALATION]: The skill documentation includes setup instructions that require elevated system permissions for environmental configuration.
- Instructs the user to run
sudo safaridriver --enableon macOS systems to permit the automated browser verification pass to control Safari.
Audit Metadata