Back to skill

Security audit

Model Pilot

Security checks for vulnerabilities and agentic risk

Overview

This skill only advises on model choice and pricing, with disclosed web lookups and no executable code or hidden persistence.

Install only if you want the agent to make model-cost recommendations and perform live pricing lookups. Review any suggested model switch yourself, especially when quality or provider choice matters, and keep pricing estimates treated as advisory.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

md
- Does NOT switch models automatically — recommends only
- Does NOT persist anything
- Does NOT access credentials
- Does NOT modify any files

## More by TommoT2

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill states 'Detect from user's message language. Default: English.' This sets a language default that may override user preference when language is unclear, and the file does not present this as an explicit opt-in choice.

Content

No source excerpt is available for this finding.