Back to skill

Security audit

Onboarding Cro

Security checks for vulnerabilities and agentic risk

Overview

This skill provides onboarding conversion advice and does not request unusual access, persistence, code execution, or hidden behavior.

Before installing, expect this skill to guide onboarding and activation strategy and to read a local product marketing context file if one exists. Its main caveat is scope overlap with signup, retention, or email-sequence work, so users should choose the more specific skill when the task is not about post-signup first-run activation.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill's invocation description is overly broad and includes general retention and engagement problems that may overlap with adjacent skills. This can cause the agent to select this skill in situations outside its intended scope, leading to irrelevant guidance, missed use of more appropriate skills, and degraded reliability of task routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The evaluation explicitly rewards the skill for triggering on very casual language like 'users sign up but then never come back' without requiring stronger scope checks. That can cause over-broad activation of the onboarding skill in ambiguous situations, increasing the chance the agent applies the wrong guidance or overrides a more appropriate skill, especially because the skill already has broad routing language around activation, retention, and first-session problems.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.