auditing-permission-ux

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill suggests running a shell command to execute a local script: bash skills/auditing-permission-ux/scripts/generate-permission-ux-audit-report.sh. This allows the agent to execute code within the local environment.
  • [PROMPT_INJECTION]: The skill analyzes untrusted user-provided descriptions of application UI and logic, which constitutes an indirect prompt injection surface.
  • Ingestion points: User-provided inputs describing app platforms, flow entry points, and UI copy in SKILL.md.
  • Boundary markers: None identified. The skill lacks delimiters or explicit warnings to separate user data from instructions.
  • Capability inventory: Includes shell script execution via bash for report generation.
  • Sanitization: There is no evidence of input validation or escaping for the data being audited.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 01:02 AM
Security Audit — agent-trust-hub — auditing-permission-ux