Back to skill

Security audit

Playbook Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guided YAML playbook generator, with some review-needed file-output and YAML-safety caveats but no hidden execution or credential behavior.

Install is reasonable if you want an assistant to draft outbound-call playbook YAML. Before saving or importing output, preview the parsed YAML, validate identifiers such as playbook_id, check that no existing file will be overwritten, and be especially careful with playbooks that affect regulated collection, credit, insurance, or telesales workflows.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:103
Finding

Unescaped User Input Can Alter Generated YAML Structure

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
SKILL.md:185
Finding

Generated Playbooks May Overwrite Existing Files

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to write a YAML file to a local path (playbooks/imported/{playbook_id}.yaml) without requiring explicit user confirmation or warning that local files may be modified. In an agent environment with filesystem access, this can cause unintended state changes, overwrite existing files, or be abused through unsafe filename handling if playbook_id is not strictly validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The validation checklist requires display_name to be Chinese and the workflow is written to steer output and user interaction toward Chinese without offering a language choice. While this is not a classic security flaw, it is a policy and safety concern because it can restrict user comprehension, reduce informed consent around generated content, and increase the chance of operator error in multilingual environments.

Content

No source excerpt is available for this finding.