The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute various local system commands and development tools to build, test, and commit code. These include git, dotnet build, pytest, cdk synth, npx ng build, grep, and pip. These operations are standard and necessary for the skill's stated purpose of software implementation and verification.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing task instructions from project files. 1. Ingestion points: Reads task specifications and definition of done from files located in Docs/In-Progress/. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are mentioned when reading these task files. 3. Capability inventory: The skill has significant capabilities, including the ability to write to the file system, execute arbitrary build/test tools, and perform git operations. 4. Sanitization: No sanitization or validation of the ingested task data is described before the agent processes it.

implement-task