The Agent Skills Directory

[Prompt Injection] (SAFE): No override markers, role-play injections, or instructions to ignore safety guidelines were detected in the skill description or example questions.
[Data Exposure & Exfiltration] (SAFE): The skill does not contain hardcoded credentials, API keys, or requests to access sensitive system files (e.g., ~/.ssh). The tools described appear to be read-only operations for deployment status.
[Obfuscation] (SAFE): No Base64, zero-width characters, or homoglyph attacks were found. The text is clear and human-readable.
[Unverifiable Dependencies & RCE] (SAFE): The skill contains no code or package manifests (e.g., requirements.txt or package.json). There are no commands to download or execute remote scripts.
[Indirect Prompt Injection] (LOW): The skill is designed to process data from external UniFi deployment logs and configurations, which constitutes an ingestion surface for untrusted data.
Ingestion points: Data returned by the list_deployments and get_deployment_details tools.
Boundary markers: Not defined in the markdown documentation.
Capability inventory: No code is provided with this skill; capabilities depend on the agent's implementation of the defined tools.
Sanitization: No specific sanitization or validation logic is mentioned for the data returned by the infrastructure tools.

deployment-management