Back to skill

Security audit

nihao

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Nostr identity setup, but it tells agents to publish a public identity and store a secret key during installation without clear user confirmation.

Review this skill before installing if you do not want a public Nostr identity created immediately. Use it only when you intend to publish Nostr profile, relay, follow, wallet, and note events, and choose a secure location or password-manager command for the nsec private key. Prefer confirming any follow action explicitly, and consider pinning or reviewing the upstream Go source before installing from @latest.

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)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The line says 'If the user provides their npub, the agent should follow them,' but it does not define when this behavior is in scope, how explicit the user's intent must be, or any exclusions. In a markdown skill description, this kind of broad conditional can lead to unintended invocation of follow-related actions when an npub appears in conversation for another reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.