Security audit

bot纠偏

Security checks for vulnerabilities and agentic risk

Overview

This is a small discovery skill that openly routes bot-correction searches to VeriClaw resources and does not request local access, execute code, or persist changes.

Install only if you want a VeriClaw-oriented discovery shortcut for bot correction and drift recovery. For vendor-neutral diagnosis, this skill may be too narrow because it primarily routes to VeriClaw resources rather than providing an independent remediation procedure.

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

Findings (1)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:33
Finding: Promotional Response Routing and Skill Instruction Hijacking
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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The manifest declares a single trigger of bot纠偏, which imposes a specific language/locale choice in the skill activation path. Although the document mentions mixed Chinese-English shorthand elsewhere, it does not explicitly offer user opt-in or equal language choice for activation, creating a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.