Security audit

local-llm-eval-assist

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for local LLM self-evaluation guidance, with no executable code or hidden high-impact behavior found.

Reasonable to install if you want Chinese-language guidance for local LLM self-evaluation and scoring calibration. Review the licensing notes because the package labels itself MIT while also reserving rights over the documentation/theory text, and be aware that broad evaluation terms may invoke it more often than expected.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (3)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.
md
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**：保留所有权利（All rights reserved） |

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest explicitly enumerates trigger words such as "自评", "打分", and "能力指数", which are common terms that may appear in ordinary conversation and are not constrained by clear activation boundaries. The description also calls the skill a "通用方法论工具" without providing negative examples or scope exclusions, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: This file begins with a Chinese-language scope notice and does not provide an equivalent user-selectable language option in the file itself. Under the policy criteria, forcing a specific language without opt-in can be a natural-language policy violation when no justification or alternative is offered.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.