Back to skill

Security audit

strategic-compact

Security checks for vulnerabilities and agentic risk

Overview

The skill provides context-management guidance and a local reminder script, with optional scheduling that users configure themselves.

Save important task notes before compacting. Enable hooks or scheduling only if you want recurring reminders, and correct the cron script path first. Counter files live in your user state directory, despite the guide's outdated /tmp instructions. Host-specific integrations remain untested.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied cron entry introduces an automatic schedule unrelated to the declared logical-boundary and context-pressure triggers. Although the script name suggests a compaction-related function, its contents are not supplied, so the evidence establishes scheduled invocation—not that compaction itself occurs automatically.

Content

No source excerpt is available for this finding.

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

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.

Trigger phrases include ambiguous standalone terms such as "compact" and "phase transition" without requiring a context-compaction request.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

These phrases can occur in unrelated requests, such as requests for compact formatting or discussions of physical phase transitions. The skill does not specify that they must refer to conversation-context management or provide exclusions, creating a risk of unintended activation.

Content

No source excerpt is available for this finding.