The Agent Skills Directory

[COMMAND_EXECUTION]: The skill employs ironbee-browser-devtools-cli and ironbee-node-devtools-cli to perform application monitoring. These tools interact with browser sessions and Node.js processes to retrieve debugging information like trace IDs, console messages, and HTTP request headers.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data from external sources during monitoring tasks.
Ingestion points: External data enters the agent context through the get-console-messages, get-http-requests, and get-logs commands in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions to ignore embedded content within the ingested logs or headers.
Capability inventory: The skill utilizes vendor CLI tools for process debugging, network monitoring, and tracing context management as defined in SKILL.md.
Sanitization: No evidence of data sanitization or validation of the retrieved content is present.

observability