Ansible Playbook Dry-Run Analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary purpose is the execution of shell commands, specifically
ansible-playbookin check and diff modes, to analyze infrastructure changes. - [EXTERNAL_DOWNLOADS]: The documentation provides commands to install the skill package from an external repository using
npx. - [PROMPT_INJECTION]: The skill processes structured and unstructured data from Ansible's outputs, creating a surface for indirect prompt injection. 1. Ingestion points: Ansible task results, JSON callback data, and diff output. 2. Boundary markers: No markers or instructions to ignore embedded content are described. 3. Capability inventory: Shell command execution via Ansible. 4. Sanitization: No validation or sanitization of the ingested data is mentioned in the documentation.
- [PROMPT_INJECTION]: The frontmatter metadata field
verification: security_reviewedis a self-authoritative safety claim that is disregarded per the evaluation policy. - [NO_CODE]: The provided skill package contains only documentation in the
SKILL.mdfile and no executable scripts or source code for direct analysis.
Audit Metadata