ClawHub
Back to skill

Security audit

Adaptive Memory

Security checks for vulnerabilities and agentic risk

Overview

This skill creates a local, workspace-scoped memory system for agents, and its persistence behavior is disclosed and aligned with that purpose.

Install this only if you want an agent to keep local project memory across sessions. Review what gets written to memory files, keep them out of public repositories if they contain private operational context, and prefer manual or clearly user-approved distillation unless you intentionally want scheduled automation.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
91% confidence
Finding

The skill’s activation guidance is overly broad and can cause it to trigger in many ordinary conversations involving context, memory, or setup. Overbroad activation increases the chance that the agent will read, create, or rely on persistent memory files without a narrowly scoped user request, which can lead to unnecessary data retention and cross-session context exposure.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
88% confidence
Finding

This section instructs the agent to create and maintain append-only daily notes containing decisions, discoveries, errors, and future-use context across sessions. Even though framed as productivity tooling, it establishes persistent storage of potentially sensitive operational context, creating privacy and data-retention risk if the memory files are accessed by other tools, users, or later sessions without strict controls.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

text

**Rules:**
- Create `memory/` directory if it doesn't exist
- One file per day, named `YYYY-MM-DD.md`
- Append throughout the day, don't restructure
- Include: decisions, discoveries, errors, context that future-you needs

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.

md
### Security Rules

- **Never write secrets** (API keys, passwords, tokens) to memory files
- Reference paths instead: "Auth config: `~/.secrets/service.env`"
- If a credential appears in chat, acknowledge it without repeating the value
- Memory files may be shared or version-controlled — treat them as semi-public