aap-lint
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository (sibilleb/AAP-Enterprise-MCP-Server) for the Model Context Protocol (MCP) server implementation.- [COMMAND_EXECUTION]: The skill interfaces with the ansible-lint command-line tool via a Python-based MCP server (uv run ansible-lint.py) to perform validation tasks.- [PROMPT_INJECTION]: The skill processes external Ansible files (playbooks, roles) which constitutes an indirect prompt injection surface.
- Ingestion points: The lint_file, lint_playbook, lint_role, and analyze_project tools read local Ansible project files.
- Boundary markers: No explicit boundary markers or directives to ignore embedded instructions are specified for the ingested content.
- Capability inventory: The skill executes ansible-lint via a shell-based MCP server.
- Sanitization: The skill relies on ansible-lint's internal parsing logic; no additional sanitization of file content is performed.- [SAFE]: No malicious behaviors such as exfiltration, obfuscation, or persistence mechanisms were detected in the skill instructions.
Audit Metadata