skills/kevinslin/skills/ag-ledger/Gen Agent Trust Hub

ag-ledger

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely on the local filesystem, storing data and state in the user's home directory (~/.llm/ag-ledger).
  • [SAFE]: No network operations, external downloads, or exfiltration patterns were detected; all data handling is restricted to the local workstation.
  • [SAFE]: The implementation uses standard Python libraries and does not include any external package dependencies or remote script execution.
  • [SAFE]: Subprocess calls identified in the static analysis are contained within integration tests and are used solely to execute the skill's own CLI for testing purposes.
  • [SAFE]: The design explicitly avoids modifying shared instructions like AGENTS.md, reducing the surface area for prompt injection attacks by using a separate, append-only ledger format.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 11:13 PM
Security Audit — agent-trust-hub — ag-ledger