Back to skill

Security audit

running-coach

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates the running-coach skill benign with medium confidence: the scanners found no AIG issues and one concern about automatically saving weekly plan and profile updates without notice.

The verdict is benign, but consider whether you are comfortable with the reported automatic updates to saved plans and profile parameters. The scan was partial because some local references could not be resolved, so its evidence is incomplete.

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
  • 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 automatically updates stored plans and profile parameters without requiring user-facing notice of those changes.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow requires logging results, editing next week's plan immediately, and writing revised parameters back to the profile. Because merely sharing a weekly activity summary can activate this workflow (L03), these persistent changes can go beyond the user's request for a review, yet no instruction requires warning the user before making them.

Content

No source excerpt is available for this finding.