The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script scripts/skillsrc.py using uv run to manage configuration in .draekien/.skillsrc. User-provided directory paths are passed as arguments to this script when persisting custom output locations, which is a common pattern but presents a surface for command injection if the execution environment does not properly handle argument escaping.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to analyze existing project code. Maliciously crafted code or comments could attempt to subvert the agent's instructions during the audit process.
Ingestion points: Source code from the project is read and processed during the 'Understanding the module' phase in SKILL.md.
Boundary markers: No delimiters or safety instructions (e.g., 'ignore embedded instructions') are used to separate the untrusted code content from the agent's instructions.
Capability inventory: The skill has the capability to write files to the local system (design specs) and execute a local Python script via uv run.
Sanitization: No sanitization or filtering of the analyzed source code is described or performed.

module-design