skills/kriscard/skills/maintain/Gen Agent Trust Hub

maintain

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill adheres to the principle of least privilege by defaulting to a read-only diagnostic mode. It explicitly states that it will not modify any files without a separate, explicit instruction from the user.
  • [COMMAND_EXECUTION]: The skill utilizes a local obsidian CLI tool for vault auditing (e.g., obsidian orphans, obsidian unresolved, obsidian tags). These operations are restricted to diagnosing vault metadata and do not involve unauthorized file system access outside the vault or arbitrary command execution.
  • [DATA_EXFILTRATION]: No network activity or attempts to access sensitive system locations (such as .ssh or .aws directories) were found. The diagnostic data is presented directly to the user.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety guardrails or override system prompts. The instructional tone is consistent with the stated diagnostic purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:36 PM
Security Audit — agent-trust-hub — maintain