autoresearch
What this skill does
Autonomous LLM training optimization research agent
github/theneoai - Code Execution - 118 stars
Threat analysis
Skill info
pkg:github/theneoai/awesome-skills@61fe4f2?skill=autoresearchAssessments (2)
Code Execution
Code Execution via local-llm-review
program.md
The skill's instructions include a loop that runs 'uv run train.py' and commits changes to git without user confirmation. This could be used to execute arbitrary code on the user's system if the agentData Manipulation
Data Manipulation via local-llm-review
program.md
The skill's instructions include modifying 'train.py' and committing changes to git without user confirmation. This could lead to unintended modifications of the user's codebase if the agent is comproBadge
Add the Anomity scan badge for autoresearch to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of autoresearch? Report an issue or request a rescan.
