ClawHub
Back to skill

Security audit

Coding

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly stores local coding preferences, but one reference file ambiguously tells agents to update the skill instructions themselves.

Install only if you are comfortable with a local coding-preference memory under ~/coding/. Before use, the publisher should correct the criteria.md references to updating SKILL.md so the skill clearly stores preferences only in ~/coding/memory.md after explicit confirmation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
93% confidence
Finding

The file explicitly instructs the agent to consult this content when deciding whether to update SKILL.md, which enables persistent self-modification of the skill's memory or behavior. Even though the content appears administrative and preference-oriented, allowing a skill to influence future writes to persistent instruction files creates a cross-session prompt-injection and integrity risk if adversarial or mistaken preferences are captured.

Content

Scanner excerpt · criteria.md (reported line 3)May include surrounding context.

md
# Criteria for Code Preferences

Reference only — consult when deciding whether to update SKILL.md.

## When to Add

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
This skill NEVER:
- Reads project files to infer preferences
- Observes coding patterns without consent
- Makes network requests
- Reads files outside `~/coding/`
- Modifies its own SKILL.md

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 98)May include surrounding context.

md
## Common Traps

- Adding preferences without confirmation → user loses trust
- Inferring from project structure → privacy violation
- Exceeding 100 lines → context bloat
- Vague entries ("good code") → useless, be specific

Static analysis

No suspicious patterns detected.