The Agent Skills Directory

[SAFE]: No malicious behavior, prompt injections, or unauthorized data access patterns were identified. The skill's primary function is to guide the agent in generating Markdown-based implementation plans for developers.
[PROMPT_INJECTION]: The skill functions by processing user-provided requirements to generate task lists. This presents a potential surface for indirect prompt injection, where malicious input in a requirement could attempt to manipulate the generated plan. However, this is a common risk for any code-generation tool and is not exploited by the skill's own logic.
Ingestion points: User-provided specifications or requirements (untrusted data) used to populate implementation plans.
Boundary markers: None explicitly defined to isolate user input from the generated instructions.
Capability inventory: The skill specifies writing files to the local file system (e.g., docs/plans/) and executing shell commands (e.g., pytest, git) via separate execution skills.
Sanitization: Not present; the skill relies on the agent's interpretation of user input to generate the plan.
[COMMAND_EXECUTION]: The skill templates include standard development commands like pytest and git commit. These are contextually appropriate for the skill's purpose and do not represent unauthorized command execution.

writing-plans