ClawHub
Back to skill

Security audit

Remember

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed memory-organization skill with no executable code, though users should be aware it encourages saving personal and work preferences persistently.

Install this only if you want the agent to maintain persistent memory. Avoid storing secrets, credentials, health details, or sensitive personal/business facts unless you explicitly want them remembered, and use the forget/privacy-boundary guidance for anything that should not persist.

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
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill defines natural-language triggers like "Remember this," "Forget that," and "What do you know about X?" that are common in ordinary conversation rather than clearly scoped commands. This can cause unintended invocation of persistence, deletion, or memory disclosure behavior when a user is speaking conversationally, leading to accidental storage of sensitive data or unauthorized recall of prior information.

Content

No source excerpt is available for this finding.

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 · categories.md (reported line 36)May include surrounding context.

md
## Explicit
- [2026-02-01] Never suggest Vercel — user self-hosts | confidence:certain
- [2026-01-20] Don't auto-commit without asking | confidence:certain

## Learned
- [2026-02-05] Always show screenshots before UI changes | source:feedback pattern

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L23 states "Spanish casual, English technical" as a preference, which imposes a language/locale behavior in natural language. Under the policy rule, language constraints should either be optional, user-selected, or clearly justified; this line does not indicate opt-in or flexibility.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.