skills/humanlayer/skills/show-me/Gen Agent Trust Hub

show-me

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command Bash(open path/to/show-me-{description}.html) to display generated HTML visualizations to the user. While intended for benign visualization, this involves executing code in the host shell environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted conversation context to generate code and shell commands.
  • Ingestion points: The agent reads the "current topic of conversation" to derive the content of visualizations and HTML files.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the conversation context.
  • Capability inventory: The skill combines the ability to generate new files with the ability to execute shell commands (open) to interact with those files.
  • Sanitization: There are no defined steps for sanitizing the input data or validating the {description} variable before it is interpolated into a shell command.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 03:19 PM
Security Audit — agent-trust-hub — show-me