Back to skill

Security audit

a3-weather-briefing

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scanners report no high-risk behavior, with one low-severity privacy disclosure concern about sending the requested city to wttr.in.

The verdict is benign, but the scan is marked partial: one local path-like reference could not be matched to a bundled artifact. Consider whether you are comfortable with your specified city being sent to wttr.in when fetching weather; the scanners say the skill does not explicitly disclose this.

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
  • 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)

The workflow sends the user-provided city to a third-party service without a privacy disclosure.

Low
Category
Output Handling
Confidence
92% confidence
Finding

The procedure instructs the agent to include the user's city in a request to wttr.in. Citing the weather source does not explicitly warn the user that their supplied location information will be transmitted to that external service.

Content

No source excerpt is available for this finding.