The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides a shell command template for the agent to verify API connectivity.
Evidence: SKILL.md contains curl -s -H "Authorization: Bearer $NETBOX_TOKEN" "$NETBOX_URL/api/plugins/changes/change-requests/" | python -m json.tool.
The command utilizes shell environment variables for sensitive authentication data and the target URL, which is a standard pattern but requires the execution environment to ensure variable safety.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing data from an external source (NetBox API).
Ingestion points: The agent is instructed to list and read Change Requests, reviews, and comments via endpoints described in SKILL.md and references/api-patterns.md.
Boundary markers: There are no instructions for the agent to use specific delimiters or protective headers to isolate untrusted content (like user-provided CR summaries) from its own instructions.
Capability inventory: The skill utilizes network access (via curl and MCP) and shell command execution.
Sanitization: No sanitization or validation logic is provided for the text content retrieved from the NetBox plugin API before it is processed by the agent.

netbox-changes