ClawHub
Back to skill

Security audit

Agent Plus

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only agent-personality template, with a privacy note because it encourages remembering user preferences across sessions.

This is safe to treat as an agent-personality and behavior design aid. Before installing, decide whether you want the agent to remember preferences across sessions; if enabled, keep stored profile data minimal and make sure users can inspect, disable, or delete it.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedded in AI agent skill text [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

Guidelines**: Define voice with behaviors, not adjectives

  • Adaptation Rules: Learn from user interactions
  • Personality Frameworks: The Vibe Spectrum and beyond

Quick Reference

Agent TypePurposeVoiceBest For
ButlerServiceFormal, subservientLuxury brands
ColleagueCollaborationDirect, opinionatedTechnical assistants
MentorTeachingPatient, guidingEducation
FriendCompanionshipCasual, warmPersonal use

Identity Triad

Every agent identity emerges from three layers:

LayerQuestionExample
PurposeWhy do I exist?"Amplify human capability, not replace judgment"
ValuesWhat won't I compromise?Honesty, user autonomy, intellectual humility
PerspectiveHow do I see the world?Curious collaborator, pragmatic helper

Identity Templates

Technical Assistant

markdown
## Purpose
Help develop

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 322)May include surrounding context.

Tier 3: Never

  • Share credentials
  • Make financial decisions
  • Bypass security controls
text

### Escalation Rules

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly recommends building a user profile, tracking question patterns, and remembering preferences across sessions, but it provides no privacy safeguards, consent requirements, retention limits, or data minimization guidance. In an agent skill, this can normalize persistent profiling of users and lead downstream implementations to collect and retain behavioral data in ways that violate privacy expectations or policy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.