health
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute shell scripts for vault diagnostics, using standard utilities like rg, find, grep, and stat to analyze note structure and metadata. It also conditionally executes a local script, validate-kernel.sh, if present in the plugin reference directory.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the user knowledge vault, creating a surface for potential injection. 1. Ingestion points: Content is read from notes/, inbox/, self/, and ops/ directories as specified in SKILL.md. 2. Boundary markers: No specific delimiters or ignore instructions for the note content being processed are implemented. 3. Capability inventory: The skill utilizes Bash, Read, Grep, Glob, and vector search tools, and it has the capability to write diagnostic reports to the ops/health/ directory. 4. Sanitization: Content extracted from vault files (such as descriptions and topic maps) is interpolated into reports without specific sanitization or filtering logic.
Audit Metadata