job-template-creator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs file system writes and Git operations (git add, git commit, git push) to manage Ansible playbooks within a user's repository. These operations include human-in-the-loop confirmation checkpoints to mitigate risk.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests and processes playbook content provided by the playbook-executor skill.
  • Ingestion points: Playbook content and filenames are received as context from the playbook-executor skill in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the playbook content are defined.
  • Capability inventory: The skill can write files, execute Git commands, and interact with the Ansible Automation Platform (AAP) API via MCP tools.
  • Sanitization: No sanitization or validation of the playbook content is performed before it is written to the repository or used in instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 06:05 PM