The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands including cargo test and make test to build the policy project and execute unit tests. This is a standard and expected part of the developer workflow described in the skill.
[INDIRECT_PROMPT_INJECTION]: The skill manages a workflow where external templates and user-provided configuration data are used to generate and edit Rust source files and execute shell commands.
Ingestion points: Rust source templates provided within the skill's file structure and user input describing policy logic and configuration.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are present in the provided templates to isolate user-controlled data.
Capability inventory: The skill utilizes Bash for command execution, alongside Write and Edit for file system modifications.
Sanitization: There is no evidence of explicit validation or sanitization of input data before it is written to the file system or passed to build commands.

pdk-unit