ClawHub
Back to skill

Security audit

stakeholder-briefing-studio

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only briefing helper that classifies audience readiness and composes approved briefing sections without requesting credentials, file access, persistence, or external execution.

This skill is reasonable to install for stakeholder briefing work. Users should still avoid pasting confidential draft material unless they are comfortable processing it in their current agent session, but the artifact itself does not add unusual access or execution behavior.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
assuming that draft material is ready for external circulation. Record which
section tags belong in the selected view and which tags must remain outside it.

### Output rule

Return `audience_mode` as a short policy string. It should name the chosen
audience, list the section classes that may be included, and state how to handle
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Static analysis

No suspicious patterns detected.