Back to skill

Security audit

dalio-macro-analysis

Security checks for vulnerabilities and agentic risk

Overview

The scanners classified this skill as benign with medium confidence, reporting one low-severity concern about an overly broad trigger and incomplete review of referenced files.

Before installing, consider whether the broad trigger could lead to unwanted macro or investment analysis. The review did not include several referenced files, so the evidence is incomplete.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 standalone trigger “原则” (“principles”) is too broad for a Dalio macro-analysis skill.

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The standalone trigger “原则” (“principles”) can match unrelated requests about general principles, potentially activating this specialized financial-analysis skill outside its intended scope. Its prescriptive macroeconomic workflow could then steer unrelated responses toward investment analysis; however, the supplied content shows no accompanying privilege escalation, exfiltration, or security-control bypass, so the impact is limited and depends on how triggers are matched.

Content

No source excerpt is available for this finding.