ClawHub
Back to skill

Security audit

Fresh Session Handoff

Security checks for vulnerabilities and agentic risk

Overview

This skill only formats a short session handoff and does not install code or run commands, though users should avoid putting real secrets in the summary.

Before installing, note that generated handoff summaries may include sensitive context already present in the chat. Ask the agent to redact passwords, API keys, tokens, or private credentials before pasting the handoff into a new session.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · agents/openai.yaml (reported line 7)May include surrounding context.

yaml
default_prompt: |
  Generate a compact handoff summary for continuing the current task in a fresh session after /new or /reset.

  OUTPUT RULES:
  - Reply in Simplified Chinese unless the user clearly asks otherwise.
  - Output only the handoff summary. Do not add an intro or explanation.
  - Keep it short, direct, and concrete.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction "Write in 简体中文 unless the user clearly asks otherwise" imposes a specific language as the default behavior. This is a natural-language policy concern because it forces a locale/language choice unless the user actively opts out, rather than offering a neutral default or explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The prompt instructs the skill to 'Reply in Simplified Chinese unless the user clearly asks otherwise,' which imposes a language preference by default. This is a natural-language policy concern because it sets a locale/language behavior without prior opt-in, rather than neutrally matching the user's language unless requested.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.