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 initandbun run checkin the~/.config/hexdirectory to provision and validate the user's voice command configuration. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files
~/.config/hex/AGENTS.mdand~/.config/hex/.agents/skills/personal-commands/SKILL.mdto define its execution context and API understanding. - Ingestion points: The skill reads application-specific documentation and metadata files from the
~/.config/hexdirectory 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.tsand execute shell commands usingbunandhexutilities. - 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