ClawHub
Back to skill

Security audit

running-coach

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: its scans found no AIG issues and one concern about weekly review updates, while some referenced paths were not resolved.

The verdict is benign, but not risk-free. Before installing, consider whether you are comfortable with the reported possibility of persistent updates without required notice. The scan was partial: it inspected all listed components, but several path references were unresolved, so the evidence is incomplete.

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 review workflow requires persistent record, plan, and profile updates without instructing the agent to warn the user.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow mandates logging sessions, marking the week completed, editing next week's plan, and writing changed parameters back to the profile. Because the skill can activate merely when a user shares an activity summary (line 3), these instructions can alter stored user data without any required user-facing notice that the review will make persistent changes.

Content

No source excerpt is available for this finding.