ClawHub
Back to skill

Security audit

Memory Pruner

Security checks for vulnerabilities and agentic risk

Overview

The skill has a legitimate memory-cleanup purpose, but it declares a shell CLI that is not included, so its executable behavior cannot be verified for a tool that may delete or rewrite agent memory.

Review this package before installing. Ask the publisher to include the actual memory-pruner executable and clear trigger/scope rules. Do not enable automatic pruning unless dry-run, explicit confirmation, backups, and a narrow memory directory are enforced.

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)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 71)May include surrounding context.

md
- `SKILL.md` — This file

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 66)May include surrounding context.

md
- **Scoring algorithm** — Based on recency, access frequency, uniqueness
- **Category tagging** — Organize memories by type for smarter pruning
- **Safe defaults** — Never deletes without confirmation (dry-run first)
- **Backup** — Creates .bak before pruning

## Files

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest file describes the skill as providing "Intelligent memory management for agents" and "Keep only what matters, prune the rest," but it does not define when the skill should be invoked or what specific requests should trigger it. The phrasing is broad enough to overlap with many general memory or optimization requests, increasing the risk of unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.