show-me

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the AI to use a shell command to open generated HTML files for the user to view the visualizations.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests conversation data to generate visual content.
  • Ingestion points: Processes the current conversation topic.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the prompt instructions.
  • Capability inventory: Includes the ability to generate files and execute shell commands to open them.
  • Sanitization: No explicit sanitization or escaping of user-provided content is defined before it is included in the visual artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 05:51 PM
Security Audit — agent-trust-hub — show-me