The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code (scripts or applications), which serves as an external data source. This creates a surface for indirect prompt injection where adversarial instructions embedded in the code under review could attempt to influence the agent's auditing logic.
Ingestion points: User-provided code snippets or files interacting with NetBox APIs are the primary inputs for this skill.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or specific "ignore instructions" prompts when processing the target code.
Capability inventory: The skill performs complex analysis, error checking, and potentially interacts with an MCP server to validate schemas.
Sanitization: There are no instructions for sanitizing or escaping the content of the scripts being reviewed before they are processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill directs the agent to consult official NetBox documentation and community-maintained SDK repositories on GitHub (such as netboxlabs.com and github.com/netbox-community) to ensure the accuracy of the review. These references target the official resources of the tool being integrated and are appropriate for the skill's stated purpose.

netbox-review-integration