vault-operations
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected in the skill instructions. The functionality is focused on local data management and productivity.
- [COMMAND_EXECUTION]: The skill uses local CLI commands to interact with its core logic, specifically invoking
python vault_v2.pyfor tasks such as capturing data, searching, and managing project status. This is standard behavior for its documented purpose. - [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by ingesting and processing untrusted user data via the
smart_capture()andsmart_search()functions. - Ingestion points: User-provided text strings in the
SKILL.mdusage examples. - Boundary markers: None present in the documentation.
- Capability inventory: Database writes (people, tasks, projects) and local command execution via
vault_v2.py. - Sanitization: Not mentioned in the provided documentation. This finding is considered low risk as it is intrinsic to the skill's primary function.
Audit Metadata