ClawHub
Back to skill

Security audit

Summarize

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with medium confidence: they found a conditional privacy concern about sending summarized local-file contents to an external model provider, and the inspection was partial because a referenced path was missing.

Before using local-file summarization, check which provider is configured and whether you are comfortable sending the file contents to it. Avoid sending sensitive information unless you have confirmed the data handling you need. The scan was partial: a local path-like reference was not found in the bundled artifact, so the results do not establish that every referenced item was inspected.

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 extracted content may be sent to an external model provider.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The quick-start instructions encourage summarizing local files without explaining that extracted contents may be transmitted to the configured external model provider. Although remote-provider use is suggested by the API-key documentation, it does not clearly disclose the local-file data flow, creating a risk of unintended disclosure of confidential or personal information. This is a conditional privacy risk, not evidence of deliberate exfiltration; actual exposure depends on the selected provider and file contents.

Content

No source excerpt is available for this finding.