show-me

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use a bash tool to open HTML files using the pattern open path/to/show-me-{description}.html.
  • [INDIRECT_PROMPT_INJECTION]: The skill generates content and tool parameters based on conversation data which could potentially contain malicious instructions.
  • Ingestion points: The "current topic of conversation" as described in SKILL.md serves as the primary data source.
  • Boundary markers: Absent; no instructions are provided to delimit or ignore instructions embedded within the conversation data.
  • Capability inventory: File writing (for HTML artifact generation) and bash command execution for opening files.
  • Sanitization: Absent; the {description} variable is used directly in a shell command path without explicit validation or escaping instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:01 AM
Security Audit — agent-trust-hub — show-me