The Agent Skills Directory

[SAFE]: The skill provides instructions for a standard developer workflow, focusing on reading task requirements and implementing code changes with validation steps.
[PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill processes untrusted data from external files, although no active exploitation was found.
Ingestion points: Reads task-related files such as design.md, plan.md, and plan-fix{n}.md, as well as existing source code.
Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the processed files.
Capability inventory: The skill has the capability to modify project files and execute shell commands for validation (e.g., tests, linting, type checks).
Sanitization: No sanitization or validation of the input file content is defined before the agent processes or acts upon the information.

exec-plan