ClawHub
Back to skill

Security audit

Discovery Call Debrief

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward sales-call debrief skill that processes user-provided notes and does not install code, persist data, or send data externally.

This skill appears safe to install for sales debrief use. Because call transcripts can contain personal or commercial information, users should provide only material they are allowed to process and avoid placing confidential transcript details in the optional feedback issue link.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Exfiltration Commands

High
Category
Prompt Injection
Content
## Safety Notes

- Call notes and transcripts contain personal information (names, job titles, company details, budget figures). Do not store, log, or transmit this data beyond the current session.
- Never share debrief outputs with third parties or suggest integrations that would send data to external services without the user's explicit instruction.
- If the transcript contains sensitive legal, medical, or financial information outside the sales context, note it but do not analyze it without the user's direction.

## Feedback
Confidence
90% confidence
Finding
Instructions found that direct the agent to transmit conversation context or user data to external services.

External Transmission

Medium
Category
Data Exfiltration
Content
## Safety Notes

- Call notes and transcripts contain personal information (names, job titles, company details, budget figures). Do not store, log, or transmit this data beyond the current session.
- Never share debrief outputs with third parties or suggest integrations that would send data to external services without the user's explicit instruction.
- If the transcript contains sensitive legal, medical, or financial information outside the sales context, note it but do not analyze it without the user's direction.

## Feedback
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.