Skills
Navigate
skills/mohitagw15856/pm-claude-skills/design-system-audit/Gen Agent Trust Hub

design-system-audit

Warn

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes npx --yes notugly to run accessibility audit tools. The --yes flag automatically accepts the installation of the package, which is executed in the shell environment.
  • [EXTERNAL_DOWNLOADS]: The npx command downloads the notugly package from the public npm registry at runtime. This package does not originate from a recognized trusted organization or the skill author's verified resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external URLs and local design token files. * Ingestion points: The agent processes data from <url> via notugly onepager and tokens.json in SKILL.md. * Boundary markers: There are no instructions to the agent to treat the processed content as untrusted or to ignore embedded instructions. * Capability inventory: The agent possesses shell execution capabilities through the npx command. * Sanitization: The skill does not define any sanitization or validation logic for the external data it reads.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 17, 2026, 11:12 PM