Security audit

Lightweight Autoresearch V2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed autonomous experiment loop for improving local files, with no bundled executable code or hidden persistence found.

Install only for repositories where you are comfortable letting an agent run local experiments and propose code changes. Review diffs at the stated checkpoints before allowing experiment runs, commits, or reverts.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest description includes Chinese-only invocation terms such as “自主优化” and “达尔文优化” without indicating that users may interact in other languages. This creates a locale/language policy concern because the skill appears to prefer a specific language without explicit user choice or justification as a region-specific tool.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.