The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and analyze external data such as code, logs, or system state to identify root causes.
Ingestion points: The agent is encouraged to use Read, Grep, and Bash to investigate 'unknown' causes within the project environment.
Boundary markers: The skill does not define specific markers or instructions to isolate or ignore potentially malicious commands embedded in the data being investigated.
Capability inventory: The agent has access to Read, Grep, and Bash tools as explicitly mentioned in the investigation protocol.
Sanitization: No specific sanitization or filtering logic is provided to handle untrusted content before it is processed by the agent to form the reasoning chain.

five-whys