ClawHub
Back to skill

Security audit

Hermes Self Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only Hermes self-audit checklist that schedules user-directed audit reports, with no evidence of hidden code execution or exfiltration.

Before installing, confirm you want weekly recurring Hermes audit reports, choose a trusted chat destination for delivery, and remember that the report may reveal operational details such as skill names, curator status, and memory-provider configuration.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description is entirely in Chinese and the file consistently specifies Chinese-formatted report content, such as the sample audit report and headings. The policy only permits locale constraints when the skill offers opt-in choice or clearly documents a justified region-specific limitation, which is not present here.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.

步骤 2：创建 Cronjob

bash
hermes cron create "0 10 * * 1" \
  --name "Hermes Self-Audit" \
  --deliver "feishu:<你的飞书ChatID>" \
  --skills "hermes-self-audit"

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.

步骤 2:创建 Cronjob

bash
hermes cron create "0 10 * * 1" \
  --name "Hermes Self-Audit" \
  --deliver "feishu:<你的飞书ChatID>" \
  --skills "hermes-self-audit"

Static analysis

No suspicious patterns detected.