skills-auto-activation
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a complete Node.js script (
skill-activator.js) intended to be installed and executed as a local Claude Code hook. This script runs in the user's local environment to process input and output JSON according to the hook protocol. - [PROMPT_INJECTION]: The core functionality of the skill is to programmatically inject "additionalContext" into the agent's prompt stream. This mechanism is used as a meta-instructional tool to guide the AI toward using relevant skills based on the content of the user's request, rather than attempting to bypass safety filters.
- [DATA_EXPOSURE]: The provided hook script accesses the local file system to read configuration data from
~/.claude/skill-rules.json. It does not attempt to access sensitive files like credentials or SSH keys, nor does it perform any network operations to send data externally.
Audit Metadata