ClawHub
Back to skill

Security audit

summarize

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign because they found no reported malicious behavior, though they flagged a potential privacy concern about sending local file contents to an external model.

Before installing, consider whether you are comfortable with local file contents being sent to the configured external model provider when summarizing. The scan is incomplete because a local path-like reference was unresolved, so the benign verdict does not establish that every referenced item was reviewed.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

Local-file summarization is instructed without warning that file contents may be sent to an external model provider.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill recommends summarizing local files with a CLI configured to use external model providers, without explicitly warning that extracted file contents may leave the machine. This can expose confidential documents if an agent invokes it under the assumption that local-file processing stays local; the provider and API-key documentation makes cloud processing foreseeable but does not establish informed authorization to upload sensitive content.

Content

No source excerpt is available for this finding.