ClawHub
Back to skill

Security audit

hermes-web-tools

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only troubleshooting guide for Hermes web tools and does not install code, persist changes, or mutate configuration without user direction.

Before installing, be comfortable with the skill guiding the agent to inspect your Hermes configuration and identify which web-provider API key names are present. It is designed to avoid changing settings unless you explicitly choose a fix.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Credential Access

High
Category
Privilege Escalation
Content
```bash
grep -n -A5 '^web:' ~/.hermes/config.yaml
grep -oE '^(TAVILY|EXA|FIRECRAWL|PARALLEL|KEENABLE|BRAVE_SEARCH)_API_KEY' ~/.hermes/.env
hermes plugins list | grep 'web-'        # informational only
cd ~/.hermes/hermes-agent && git log --oneline -10 -- tools/web_tools.py plugins/web/
```
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Static analysis

No suspicious patterns detected.