Back to skill

Security audit

Chatmosp Msr Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to support a real ChatMOSP calculation workflow, but it needs review because it runs unverified external Python code with unsanitized task paths and sends generated files through Feishu.

Install only if you trust the external `mosp-for-chatMOSP` copy and companion skills. Before use, restrict task names to simple safe characters, verify the engine source and commit, run it in a limited workspace without unrelated secrets, and confirm whether Feishu upload is acceptable or use a local-only workflow.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:76
Finding

Shell Command Injection Through Unquoted Task Name

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:155
Finding

Unpinned External Calculation Engine Is Executed Without Integrity Verification

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
> - If the user writes in Chinese, read `SKILL.md` in this same directory and respond in Chinese.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 176)May include surrounding context.

md
Show 5-option confirmation → User confirms → R=20Å, no warning →

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: chatmosp-msr-generator
description: |
  chatMOSP 系统的 MSR(多尺度结构重构)计算引擎。调用 mosp-for-chatMOSP/utils/msr.py

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL_cn.md (reported line 1)May include surrounding context.

md
---
name: chatmosp-msr-generator
description: |
  chatMOSP 系统的 MSR(多尺度结构重构)计算引擎。调用 mosp-for-chatMOSP/utils/msr.py

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly transmits generated files to Feishu, an external channel, but does not require any explicit user notice or consent at the point of transmission. Even if the files are scientific outputs, they may contain sensitive research data, project names, or metadata, so silent exfiltration to a third-party messaging platform creates a real privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
- ✅ Target directory has been created by file-organizer
- ✅ External `mosp-for-chatMOSP` installed, with `utils/msr.py` and `utils/paint.py`
- ❌ DO NOT bypass parameter-builder and build parameters manually
- ❌ DO NOT skip user confirmation and execute calculation directly

## 3. Input Contract (Required fields in input.json)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to transmit generated output files to Feishu, but it does not require a clear user-facing disclosure or a fresh consent check immediately before external transmission. This creates a data exfiltration/privacy risk because generated artifacts and captions may contain sensitive research parameters, filenames, or workspace-derived metadata that leave the local environment.

Content

No source excerpt is available for this finding.