ClawHub
Back to skill

Security audit

Brand Sentiment Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward brand-sentiment content-audit helper with minor scoping and documentation issues but no hidden access, persistence, or unsafe behavior found.

Install only if you want help auditing and rewriting brand content for AI-search sentiment. Be aware that the activation wording is broad and the documented commands do not fully match the bundled script, so users may need to run the script with --content or rely on the markdown guidance rather than the advertised --brand workflow.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description contains broad trigger phrases such as 'whenever the user mentions AI saying negative things about their brand' and 'improving AI brand portrayal,' which can match ordinary discussion rather than a clear request to use this skill. Over-broad activation can cause the agent to invoke the skill in contexts the user did not intend, creating scope creep, unnecessary data processing, and increased risk of unsolicited persuasive or reputation-management behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This JSON file is a manifest-like file, so vague-trigger review applies. The prompt text "Audit our brand sentiment for AI search" is a natural-language invocation with no explicit trigger boundaries, exclusions, or scope constraints, which could overlap with ordinary user requests rather than a narrowly defined activation condition.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.