The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a specific Python script (project-system.py) located within its directory structure (.claude/skills/ordinary-interfaces/scripts/) using the Bash tool. This is a functional requirement for the project scan phase of the audit.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled files from the project directory, creating a surface for indirect prompt injection.
Ingestion points: The skill ingests untrusted data when scanning the project directory using Read, Glob, and Grep tools, and through the execution of the project-system.py script.
Boundary markers: There are no boundary markers or instructions to explicitly ignore instructions embedded within the processed files.
Capability inventory: The skill possesses the Bash capability, which allows for shell command execution, alongside standard file system access.
Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content read from the external files before it is processed by the agent.

review