ClawHub
Back to skill

Security audit

tududi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward tududi API reference for managing tasks, with expected token-based access and no hidden code or persistence.

Before installing, configure TUDUDI_URL only for the tududi instance you trust and use an API token with the least access needed. Be careful with the documented DELETE operations, since they can remove tasks or inbox items if the UID is wrong.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

List tasks

bash
curl -s $TUDUDI_URL/api/v1/tasks \
  -H "Authorization: Bearer $TUDUDI_API_TOKEN"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file includes direct examples for deleting tasks via the API, but it does not warn users that the action is destructive or may permanently remove data. Under the markdown criteria for missing user warnings, operations that affect user data should include a clear warning about impact and reversibility.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documentation provides a DELETE example for inbox items but does not disclose that the action is destructive or potentially irreversible. Markdown skill docs should warn users when documented behavior can affect stored data or system state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.