pflow-ansible
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided Ansible content (playbooks, roles, tasks, etc.) and possesses the capability to write files and execute shell commands for linting and syntax checks. This environment is susceptible to indirect prompt injection if malicious instructions are embedded in the Ansible files being analyzed.
- Ingestion points: The agent reads Ansible project files from the local environment as directed by the user's task.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are implemented.
- Capability inventory: Capability to write and edit files, and execute shell commands such as ansible-lint and ansible-playbook for validation.
- Sanitization: The skill instructions emphasize secure coding practices in the generated Ansible output (e.g., using command instead of shell and quoting variables) which mitigates execution risks, although it does not filter the input data for prompt injection specifically.
Audit Metadata