Back to skill

Security audit

Agent Org Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for setting up agent-team workflows; it does promote scheduled autonomous work, but that behavior is disclosed and aligned with its purpose.

Install only if you want to create scheduled agent workflows. Before enabling any cron templates, confirm the writable paths, timezone, model/API budget, message targets, and pause or rollback process, and require manual review before any commit, push, release, or publish action.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill repeatedly encourages users to set up autonomous agents, cron jobs, and self-running workflows without clearly warning that these actions can modify files, send messages, consume API budget, or continue operating without active oversight. In a skill intended for organization-wide automation, omission of explicit safety gates and impact disclosures increases the chance of unintended state changes and persistent runaway behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The release and maintenance section describes automated version bumps, commits, pushes, releases, and publishing workflows, but does not require explicit human confirmation immediately before external publication or repository changes. Because these actions can be irreversible or widely propagated, the skill normalizes high-impact automation without sufficient safeguards, review checkpoints, or emergency abort conditions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The schedule configuration fixes the timezone to Asia/Shanghai in a general-purpose template, which imposes a specific locale without user opt-in. This appears again in other templates, suggesting a default locale policy that may not match all organizations using the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This daily report cron example uses Asia/Shanghai as a fixed timezone in a reusable template. Because the document presents general templates for agent organizations, forcing one locale without choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The inspection cron template sets tz to Asia/Shanghai even though the file is framed as broadly reusable templates. This enforces a specific locale setting without offering an alternative or documenting a region-specific limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Most of the operational guidance in the skill is written in Chinese, while the file metadata and surrounding framework are in English. Because the document does not state that the skill is Chinese-only or offer an alternate language option, it may violate language-choice expectations for users who cannot read Chinese.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown template directs the agent to write output to company/departments/[dept]/learning_YYYYMMDD.md, which affects user or organizational data. The surrounding description does not include any warning that the cron job will create or modify files on a recurring schedule.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The inspection template tells the agent to write patrol results to company/departments/inspector/patrol_YYYYMMDD.md, which is an automated file write. The markdown does not disclose this persistence behavior or its impact on stored organizational records.

Content

No source excerpt is available for this finding.