Back to skill

Security audit

paste-safe-pi

Security checks for vulnerabilities and agentic risk

Overview

This skill gives paste-safe shell-command formatting guidance for unreliable remote terminals, with no hidden code, network behavior, persistence, or credential handling found.

Install this only if you want the agent to format commands for unreliable hand-pasted remote shells. Review any generated sed or echo edits before pasting them, because they can modify files on the target machine.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instructions explicitly forbid any non-ASCII content, including Chinese, and direct the agent not to type Chinese into commands. This is a natural-language locale/language restriction that does not offer user opt-in or choice, so it fits the policy-violation category.

Content

No source excerpt is available for this finding.