ClawHub
Back to skill

Security audit

Build a report from agent work

Security checks for vulnerabilities and agentic risk

Overview

This skill is a reporting guide with explicit, purpose-aligned delivery examples, but users should review reports before sending them to chat platforms.

Before using the Hermes examples, review the report for secrets, personal data, regulated information, and internal-only operational details. Send only to authorized channels, and prefer summaries or redacted versions when the report contains sensitive findings.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to send reports and attachments through Hermes to external messaging platforms without any warning to review the report for sensitive, regulated, or internal-only content first. In context, this skill is explicitly meant to aggregate findings from monitoring and research, which commonly include confidential operational details, so the omission can directly lead to unintended data exfiltration or oversharing.

Static analysis

No suspicious patterns detected.