The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources and uses it to drive agent logic.
Ingestion points: In references/discovery.md, the agent executes bd timeline logs to fetch and scan raw application logs for journey events.
Boundary markers: There are no explicit delimiters or instructions to the agent to ignore embedded commands within the log data, although the skill includes a global rule requiring user approval before deployment.
Capability inventory: Across all reference files, the skill provides the agent with the ability to execute bd workflow create, bd workflow deploy, bd workflow alert upsert, and bd dashboard create commands.
Sanitization: The skill does not implement sanitization or filtering for the log content ingested into the context before the agent analyzes it for event identifiers.
[COMMAND_EXECUTION]: The skill relies on the execution of the bd CLI tool to perform discovery and deployment tasks. While this is the intended primary purpose of the skill, it involves significant interaction with the host environment through shell commands such as bd app list, bd workflow charts, and bd dashboard create.

bd-cuj