ClawHub
Back to skill

Security audit

hermes-session-retitle

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps rename Hermes session titles, with local database reads and Hermes CLI renames that match its stated purpose.

Install this only if you want an agent to inspect your local Hermes session database and rename session titles. Review the generated rename plan before applying it, especially for bulk cleanup, and keep the printed backup output if you may need to undo title changes.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs use of shell and file/database reads (`sqlite3`, `hermes`, local DB paths, helper scripts) but does not declare any explicit tool scope or allowed-tools boundary. That creates an authorization gap where an agent may invoke broader shell/file capabilities than the skill actually needs, increasing the chance of unintended local data access or command execution beyond session-title maintenance.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation cues include broad phrases like 'clean up my session list' and periodic/incremental use cases, which can cause the skill to trigger on ambiguous user requests. In context, this skill performs bulk renaming of user data, so overbroad triggering raises the risk of unintended mass changes without sufficiently explicit user confirmation.

subprocess module call

Medium
Category
Dangerous Code Execution
Content
failed = []
    for item in plan:
        proc = subprocess.run(
            ["hermes", "sessions", "rename", item["id"], item["title"]],
            capture_output=True, text=True,
        )
Confidence
70% confidence
Finding
subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Static analysis

No suspicious patterns detected.