T09 · Insecure Skill Coding Practices
- Location
SKILL.md:103- Finding
Unescaped User Input Can Alter Generated YAML Structure
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:103Unescaped User Input Can Alter Generated YAML Structure
SKILL.md:185Generated Playbooks May Overwrite Existing Files
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.
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.