Back to skill

Security audit

Claws Daily

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed news-brief skill that fetches public news and runs on a fixed Shanghai-time schedule, with no evidence of hidden or destructive behavior.

Before installing, make sure you are comfortable with a scheduled heartbeat running twice daily on Asia/Shanghai time and with your news preferences being stored in the skill metadata. The skill will call the configured news service and may use public web-fetching tools for hot topics.

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
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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description specifies that briefs are generated twice daily at 09:00 and 18:00 in Asia/Shanghai, imposing a locale-specific time basis in the user-facing behavior. This is a natural-language locale policy concern because the file does not indicate that users can choose a different timezone or explicitly opt in to this regional setting.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow states that batch determination is fixed to Asia/Shanghai, which forces a locale-specific operational behavior on all users. Although output language can vary later, the scheduling logic itself does not provide user choice or justified regional scoping.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Lines L03-L06 state that for formal output the agent must strictly follow the specified format in Chinese-context instructions, and the file presents Chinese requirements before the examples without offering a user language choice. Because language/locale policy violations apply to all file types, this is a valid finding unless the skill explicitly offers opt-in or justified locale restriction, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document states that the timezone is fixed to Asia/Shanghai and cannot be overridden. This imposes a locale-specific behavior without user opt-in, which matches the policy category for language/locale constraints.

Content

No source excerpt is available for this finding.