x9-onboarding
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local validation script (
scripts/validate_onboarding.py) and perform safe discovery checks usingcommand -vto verify the presence of prerequisite tools. These operations are limited to local, non-functional checks designed for environment verification.\n- [INDIRECT_PROMPT_INJECTION]: The skill processesonboarding.jsonfiles provided by other skill packages, creating a potential surface for indirect injection.\n - Ingestion points: External declaration files located at
skills/*/references/onboarding.json(as described inreferences/declarations.md).\n - Boundary markers: The instructions in
SKILL.mdandreferences/declarations.mdexplicitly define the content as read-only data and warn the agent not to treat it as executable instructions.\n - Capability inventory: The skill performs local tool discovery (
command -v) and executes a provided Python validator script.\n - Sanitization: The
scripts/validate_onboarding.pyscript implements rigorous sanitization, using regular expressions to reject any declaration containing shell syntax, paths, URLs, or secret-like patterns (e.g., API keys, tokens).
Audit Metadata