show-me
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on formatting and presentation logic for visualizing complex topics. It does not include any network operations, credential access, or malicious code. Notably, the instructions explicitly advise the agent to use safe platform-provided file-opening mechanisms rather than assuming the availability of potentially dangerous shell commands like 'open'.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it transforms untrusted user data into HTML artifacts for browser rendering.
- Ingestion points: User input defining topics for visualization in SKILL.md.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present.
- Capability inventory: File system write access for artifact creation and browser invocation for visualization.
- Sanitization: The skill lacks explicit instructions for sanitizing or escaping user-controlled data before it is rendered in HTML.
Audit Metadata