Back to skill

Security audit

sn-proactive-agent

Security checks for vulnerabilities and agentic risk

Overview

This skill openly records connected conversations to track projects and runs suggested follow-ups only after you accept them.

Install if you are comfortable having connected conversations stored locally and processed by your configured model service. Review each suggested action before accepting it. Verify release checksums; downloaded runtime and plugin code were not bundled here. Conversation records remain after uninstall unless you explicitly request deletion.

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)

L37 requires English-language comments in command blocks without user opt-in.

Low
Category
Output Handling
Confidence
96% confidence
Finding

The instruction requires comments inside example command blocks to be written in English. Unlike preserving executable command names and parameters, prescribing the natural language of comments is a language restriction without an offered user choice or a documented justification.

Content

No source excerpt is available for this finding.