Back to skill

Security audit

memory-checkup

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: its purpose and expected behavior look aligned, though scanners note unclear activation boundaries and undeclared tool scope.

The verdict is benign, but evidence is incomplete: Skillspector marked its analysis partial because three local path-like references in SKILL.md were unresolved, and it reported an undeclared tool scope. Before installing, consider whether you are comfortable with unclear automatic activation and file-reading scope.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The proactive trigger 'risky recall situations' lacks a clear activation boundary.

Low
Category
Trigger Abuse
Confidence
85% confidence
Finding

The explicit memory-audit request examples are specific, but the additional trigger for 'risky recall situations' does not define what makes recall risky. The example of metrics recorded over many days could cause ordinary metric-recall requests to activate the audit workflow without an audit request.

Content

No source excerpt is available for this finding.

Automatic activation relies on subjective risk and an unspecified periodic schedule.

Low
Category
Trigger Abuse
Confidence
89% confidence
Finding

The description permits activation whenever answering from memory "feels risky because facts may have drifted," without defining an observable threshold. The additional instruction to run "periodically" at L37 supplies no cadence, leaving it unclear when routine memory use should trigger an audit rather than a normal answer.

Content

No source excerpt is available for this finding.