skills/24601/augustus/augustus-train/Gen Agent Trust Hub

augustus-train

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill provides Python examples (fit.py, infer.py) that utilize joblib and pickle for model serialization. The instructions include a clear security warning stating that joblib/pickle loading can execute code and advise users to only load trusted, verified artifacts and validate bundle digests before deserialization.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external records for model training and inference, creating a surface for indirect prompt injection.
  • Ingestion points: Data is ingested via JSONL files in fit.py and infer.py, and the general workflow is described in references/data-and-splits.md.
  • Boundary markers: The skill recommends the use of explicit annotation guides and adjudication processes to verify label integrity.
  • Capability inventory: The skill performs model training using scikit-learn and inference via joblib. It also utilizes companion shell scripts for diagnostics.
  • Sanitization: Instructions in references/data-and-splits.md advise redacting private fields and removing identifiers from data before processing.
  • [EXTERNAL_DOWNLOADS]: The skill refers to installing the scikit-learn package via pip and provides links to research notes hosted in the author's official GitHub repository. These references are consistent with the identified vendor and do not involve untrusted or risky sources.
  • [COMMAND_EXECUTION]: The skill provides documentation for executing several local diagnostic scripts (policy_receipt.py, provenance_gate.py, overlap_audit.py, etc.). These scripts are intended for local development workflows and operate on user-provided data manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 06:41 AM