ClawHub
Back to skill

Security audit

Percept Summarize

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but it automatically processes and stores sensitive conversation data with unclear controls around external summarization and long-term speaker profiles.

Review this skill before installing in any environment with private, regulated, or workplace conversations. Confirm whether OpenClaw processing is local or remote, who can access the SQLite database and dashboard, whether users consent to automatic summarization, and how speaker profiles and relationship data can be deleted or expired.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly states that speaker-tagged transcripts are sent to an external CLI/LLM for summarization, but it does not warn users about that disclosure at the point of use. Conversation transcripts commonly contain sensitive personal, business, or credential-like information, so silent transfer to another tool or model can create privacy, compliance, and unintended data-sharing risk.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The retention section discloses long-lived storage of summaries, relationships, and indefinitely retained speaker profiles, but the skill does not provide a prominent privacy warning or minimization guidance. Persisting conversation-derived personal data and relationship graphs increases exposure from local compromise, insider access, secondary use, and regulatory noncompliance, especially because profiles never expire.

Static analysis

No suspicious patterns detected.