Back to skill

Security audit

api-sequence-diagram

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused code-analysis helper that reads relevant Java API code to produce a Mermaid sequence diagram, with no install scripts, persistence, network fetching, or hidden execution.

Install this if you want an agent to inspect Java API call paths and generate sequence diagrams. Be aware that using it will expose relevant repository implementation details in the agent conversation/output, so avoid running it on code you do not want summarized or shared in that context.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description uses broad trigger phrases such as analyzing interface call chains, generating sequence diagrams, and viewing interface relationships without clear boundaries or exclusions. This can cause the skill to activate in contexts beyond the user's actual intent, leading to unintended codebase traversal, over-collection of repository context, and accidental disclosure of internal architecture or sensitive implementation details.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description mandates Chinese output by default without confirming the user's language preference. While not directly enabling code execution or privilege escalation, this can override user intent, reduce usability, and create safety issues if important technical or security information is delivered in an unexpected language the user cannot accurately review.

Content

No source excerpt is available for this finding.