The Agent Skills Directory

[Indirect Prompt Injection] (LOW): A potential attack surface exists where malicious instructions embedded in security logs or incident data could influence the agent.
Ingestion points: The skill processes user-provided requests regarding incident response patterns and security tasks.
Boundary markers: Absent; the skill does not define specific delimiters or instructions for the agent to ignore commands within processed data.
Capability inventory: The skill is granted powerful tool access including Bash, Write, Edit, and Grep.
Sanitization: Absent; no explicit sanitization or validation of the input data is defined in the skill logic.
[Command Execution] (SAFE): The skill requests access to the Bash tool. This is a high-privilege capability; however, it is consistent with the stated purpose of performing advanced security incident response tasks and no malicious pre-defined commands were detected.

incident-response-planner