autoresearch

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the uv package manager installer from astral.sh, which is the official domain for the well-known Astral technology company. This is used for fast Python dependency management and execution during the research loop.
  • [REMOTE_CODE_EXECUTION]: Several scripts, including setup.sh and the instructions in SKILL.md, use the pattern curl | sh to install the uv tool. This is a standard installation method provided by the vendor and is appropriate for the skill's purpose of environment preparation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest research directives from a program.md file, which serves as an external context for the agent's autonomous decisions.
  • Ingestion points: program.md is read by the agent at the start of every experimentation iteration.
  • Boundary markers: Not present; the agent is instructed to follow the Markdown directions directly without specific delimiters.
  • Capability inventory: The agent possesses file editing capabilities (train.py), shell execution (uv run train.py), and git operations (commit, reset).
  • Sanitization: No input sanitization is performed on the directives, as they are intended for semantic interpretation by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 09:10 AM