ClawHub
Back to skill

Security audit

势 — Strategic Momentum Model

Security checks for vulnerabilities and agentic risk

Overview

The strategy-coaching skill asks agents to retain real-use failure patterns in its reusable document without approval or privacy limits.

Before sharing confidential strategy, remove the instruction to append real-use observations or require explicit approval and generalized, anonymized lessons. Keep identifiable business details out of reusable skill files.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The skill instructs agents to persist real-use failure patterns without warning users that their case details may be retained.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The instruction to add observed entries after each real use and 'paste the actual failure pattern' encourages retaining user-derived information in a reusable skill document without requiring consent or anonymization. Because this skill elicits venture strategy, partner relationships, and investment readiness, following that instruction could expose confidential business details to future users or repository readers. No automatic persistence or external transmission is shown, so the risk depends on an agent actually updating or sharing the document.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.