Security audit

SiYuan API

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is a clearly scoped local SiYuan workspace integration, with a notable caution around using API tokens over non-loopback HTTP LAN endpoints.

Install only if you intend to let the agent read and modify your SiYuan workspace. Keep SIYUAN_API_URL on localhost or 127.0.0.1 when possible; if using another LAN machine, prefer HTTPS or a trusted private network, and rotate the SiYuan token if it may have been exposed.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:135
Finding: API Token May Be Transmitted in Plaintext to a LAN Endpoint
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.