ClawHub
Back to skill

Security audit

Harvey Specter Writing Style

Security checks for vulnerabilities and agentic risk

Overview

This is a benign writing-style skill with no code or privileged behavior, though its broad trigger wording could make it apply more often than users expect.

Before installing, consider whether you want this persona to activate on broad requests like making text more confident or punchier. The skill appears safe from a security standpoint, but users who only want explicit Harvey Specter-style rewrites may prefer narrower activation wording.

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

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
95% confidence
Finding

The trigger description includes broad, everyday phrases such as 'make it more confident,' 'add swagger,' and 'make it punchier,' which can match many ordinary writing requests outside the user's intent to invoke this specific persona skill. That creates unintended activation risk, causing the agent to apply an assertive style in inappropriate contexts and potentially override a more suitable default behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.