T09 · Insecure Skill Coding Practices
- Location
SKILL.md:76- Finding
Shell Command Injection Through Unquoted Task Name
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:76Shell Command Injection Through Unquoted Task Name
SKILL.md:155Unpinned External Calculation Engine Is Executed Without Integrity Verification
Referenced artifact was not completely inspected
> - If the user writes in Chinese, read `SKILL.md` in this same directory and respond in Chinese.
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.
Show 5-option confirmation → User confirms → R=20Å, no warning →
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
---
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 were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
---
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
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.
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.
- ✅ 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)
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.