Security audit

hermes-config-change-checklist

Security checks for vulnerabilities and agentic risk

Overview

This skill provides a coherent checklist for requested Hermes configuration and skill maintenance, with safeguards for secrets, profiles, verification, and restarts.

Specify the target profile and intended changes. For bulk maintenance, review deletion candidates and keep backups. Verification may make billable provider calls or start configured MCP servers. Reports use Chinese headings.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The mandatory report templates require Chinese headings without user language opt-in.

Low

Category: Output Handling
Confidence: 98% confidence
Finding: The skill explicitly requires Chinese headings for both change reports and read-only check reports, regardless of the user's language. It provides neither a language choice nor a locale-specific justification for this output requirement.
Content: No source excerpt is available for this finding.