Security audit

Taizi Knowledge Base

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent personal knowledge-base helper, but it persists and indexes user content using broad triggers and shell-style commands without enough scope or safety controls.

Install only if you intentionally want this skill to remember and search local content. Avoid storing secrets or private files, require explicit confirmation before write or add-file actions, and use a safe wrapper that passes arguments without shell interpolation and restricts file indexing to approved directories.

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

Error

Location: SKILL.md:25
Finding: Command Injection Through Shell-Interpolated User Input
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrase is broad enough to match ordinary conversation, which can cause the skill to activate when the user did not explicitly intend to use the knowledge-base workflow. Because this skill performs storage actions and writes to persistent local locations, unintended activation could result in accidental retention of sensitive user content or files.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.