hex-personal-commands

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands hex commands init and bun run check in the ~/.config/hex directory to provision and validate the user's voice command configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files ~/.config/hex/AGENTS.md and ~/.config/hex/.agents/skills/personal-commands/SKILL.md to define its execution context and API understanding.
  • Ingestion points: The skill reads application-specific documentation and metadata files from the ~/.config/hex directory at runtime.
  • Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the ingested markdown files.
  • Capability inventory: The skill has the ability to write to hex.config.ts and execute shell commands using bun and hex utilities.
  • Sanitization: The skill does not define any sanitization or validation logic for the content read from the AGENTS.md or secondary SKILL.md files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 01:49 PM
Security Audit — agent-trust-hub — hex-personal-commands