The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from the conversation history and user arguments to perform system actions.
Ingestion points: Uses $ARGUMENTS and the general conversation context as the source for todo content (SKILL.md).
Boundary markers: The instructions do not define explicit delimiters or warnings to prevent the agent from interpreting instructions embedded within the user-provided tasks.
Capability inventory: The skill uses Bash and Write tools to create directory structures, generate files, and perform git commits based on the extracted content (SKILL.md).
Sanitization: No sanitization or validation logic for the input data is described in this instruction wrapper.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform workflow operations including directory management and version control actions. While these are part of the intended 'Get Shit Done' workflow, the execution of shell commands based on conversation context presents a potential attack surface if the underlying workflow script does not properly handle special characters in the arguments.

gsd-add-todo