ClawHub
Back to skill

Security audit

Mensa

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches public German canteen menus from OpenMensa and stores only a local canteen preference.

Install only if you are comfortable with menu/date lookups being sent to OpenMensa and with a local config file storing your chosen city and canteen. Re-run setup to change the saved default, and review the script if your runtime grants broad shell or network access to skills.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
Substring matching is normalised — special characters (`-`, `,`, `.`) are ignored, so a query like *"Otto Hahn"* matches a canteen named *"Mensa Otto-Hahn-Straße"*.
5. **"No canteen matched"?** The query did not resolve to any saved alias. Show the user the available aliases (the script prints them) and offer to re-run `--setup` for a different city.

## Output rules (strict)

When rendering the menu back to the user, follow these rules verbatim:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill instructs the agent to execute Python scripts, perform outbound network access, and create a local config file, but the manifest does not declare any explicit tool scope or permissions. This creates a least-privilege gap: a host agent may grant broader shell/file/network capabilities than the skill actually needs, increasing the blast radius if the script or surrounding instructions are abused.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.