The Agent Skills Directory

[SAFE]: The skill provides a standard template for development workflows. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
[COMMAND_EXECUTION]: The skill includes instructions to generate shell commands for pytest and git, which are necessary for the described development process.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided specifications to generate executable plans, which constitutes an attack surface. Ingestion points: Untrusted data enters the context through user-provided specifications or requirements (referenced in the description). Boundary markers: The skill does not explicitly define delimiters for the input specifications. Capability inventory: The skill allows for file creation (within docs/plans/), Python code generation, and shell command generation (pytest, git). Sanitization: There is no evidence of input validation or sanitization for the provided specifications.

writing-plans