Back to skill

Security audit

Build a report from agent work

Security checks for vulnerabilities and agentic risk

Overview

This skill is a reporting-writing guide with disclosed examples and no hidden execution or privileged behavior.

Installers should treat this as a benign report-building aid. Before using its delivery examples, confirm the Hermes target with the list command and avoid sending reports or attachments to unintended chats or channels.

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

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The sample HTML sets lang="en", which imposes an English locale in the generated report template. The skill does not indicate that language is configurable or that English is required for a region-specific purpose, so this is a natural-language locale policy issue.

Content

No source excerpt is available for this finding.