ClawHub
Back to skill

Security audit

MyLore

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly limits public posting and chapter withdrawal to user-directed actions and includes safeguards against sharing private information.

Publishing makes the story and interview answers public. Check that the proposed content contains only information you want shared, and keep the return key private because it controls future chapters and withdrawals. The artifact review does not verify the service's storage or privacy guarantees.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The code targets a chapter withdrawal endpoint rather than publishing, adding, reading, or searching stories. Withdrawing existing content is a distinct state-changing capability, not merely a supporting implementation detail of the declared functions.

Content

No source excerpt is available for this finding.

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 43)May include surrounding context.

The request

bash
curl -sS https://mylore.ai/api/lore \
  -H 'Content-Type: application/json' \
  --data @story.json