design-motion-principles

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its 'Audit Mode' which processes untrusted data.
  • Ingestion points: The skill performs 'reconnaissance' and 'motion-gap analysis' by reading the user's local codebase (SKILL.md).
  • Boundary markers: There are no instructions provided to the agent to treat the audited code as untrusted or to use delimiters to separate audited content from instructions.
  • Capability inventory: The skill possesses the ability to write files to the 'motion-audits/' directory and execute system commands to open a web browser (SKILL.md).
  • Sanitization: No sanitization or validation of the ingested code is specified, creating a risk that malicious instructions embedded in the audited project could influence the agent's behavior or the content of the generated reports.
  • [COMMAND_EXECUTION]: The skill automatically executes a command to open generated HTML reports in the default browser upon completion of an audit. While this is intended functionality, it involves the execution of shell-level operations based on skill logic.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes installation instructions that download content from a third-party repository (kylezantos/design-motion-principles) via npx (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:03 PM
Security Audit — agent-trust-hub — design-motion-principles