Back to skill

Security audit

Account Strategist

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only account strategy advisor with no executable code or install actions, though users should be careful with sensitive customer/account information they provide to it.

This skill appears safe to install for account strategy work. Treat customer org charts, usage data, revenue figures, contract details, and stakeholder sentiment as sensitive business information, and provide only the account context you are comfortable sharing with the agent.

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
97% confidence
Finding

The activation guidance says only to reference the agent by name or specialty when its expertise is needed, without defining specific trigger phrases, scope boundaries, or exclusion conditions. Terms like "specialty" and "when you need its expertise" are broad enough to overlap with ordinary discussion and could cause unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'Communication Style' section prescribes how the assistant must speak and frame responses, but it does not offer any user opt-in or flexibility for alternative language or locale preferences. Under the stated policy, forcing a specific language style without user choice can be a natural-language policy concern.

Content

No source excerpt is available for this finding.