Back to skill

Security audit

science-health-research-brief

Security checks for vulnerabilities and agentic risk

Overview

The skill openly sends research questions to Finch and Powerdrill, with clear limits on payments and wallet access.

Questions go to Finch and Powerdrill. Remove identifying medical details and confidential research, review provider privacy terms, and explicitly approve any paid run. Results are informational, not medical advice.

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 submits the user's research question to an external service without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs the agent to submit the user's research question to an external service without first checking for sensitive information or obtaining informed approval for that disclosure. Because health research questions can contain identifiable medical histories or confidential research details, this omission can expose sensitive data, although the external integration is openly described and there is no evidence of malicious intent.

Content

No source excerpt is available for this finding.