health
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute local scripts and commands such as
python3 bin/vault-health.py,python3 bin/semantic-index.py, anddream cycle. These operations allow the agent to run code within the local environment to perform vault diagnostics. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it processes content from vault notes which may contain data from untrusted external sources (e.g., web clippings or shared documents).
- Ingestion points: Markdown notes and documents located within the user's vault system.
- Boundary markers: Absent. The skill instructions do not establish delimiters to isolate note content from agent instructions during the audit.
- Capability inventory: The skill utilizes file system read access and subprocess execution (Python) to perform its functions.
- Sanitization: Absent. The skill does not describe any methods for validating, filtering, or escaping the content of notes before it is analyzed or used to generate health reports.
Audit Metadata