impeccable

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external repository at github.com/pbakaus/impeccable for live installation and directs users to https://impeccable.style for documentation.
  • [COMMAND_EXECUTION]: The skill instructions utilize npx to execute the impeccable package (npx impeccable detect) and define internal sub-commands (e.g., /impeccable init, /impeccable audit) to interact with the design tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface through commands that process local project data:
  • Ingestion points: Project files are processed by the audit, extract, and document sub-commands.
  • Boundary markers: Not specified in the skill stub.
  • Capability inventory: Shell execution capabilities are present via the npx command reference.
  • Sanitization: Not explicitly documented in the metadata; the skill relies on the underlying impeccable CLI logic for data handling.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 09:52 AM
Security Audit — agent-trust-hub — impeccable