ClawHub
Back to skill

Security audit

Call Claude Sonnet 4 Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is instruction-only, but it tries to override normal agent authority and makes meeting content an authoritative source, which users should review before installing.

Install only if you specifically want this role-play meeting workflow, and treat any meeting minutes as untrusted context. The skill should be narrowed and rewritten so it does not claim priority over platform instructions or make embedded meeting content authoritative.

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

Error
Location
SKILL.md:13
Finding

Skill instructions attempt to override the agent instruction hierarchy

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
91% confidence
Finding

The skill description is extremely broad and generic ('AI agent for call claude sonnet 4 agent tasks'), which creates an ambiguous activation surface and makes it unclear when this skill should be invoked. In agent ecosystems, vague trigger descriptions can cause inappropriate routing or over-invocation, increasing the chance that unrelated user requests are handled under this skill’s strong embedded behavioral instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.