The Agent Skills Directory

[PROMPT_INJECTION]: Potential Indirect Prompt Injection Surface. The skill analyzes source code files which may contain untrusted data. Ingestion points: Project source files defined in the manifest. Boundary markers: Absent. The skill lacks explicit delimiters or instructions to ignore embedded commands during extraction. Capability inventory: Local script execution and file writing to the project directory. Sanitization: Not specified.
[COMMAND_EXECUTION]: Local Utility Usage. The skill instructs the agent to execute specific Python utilities for internal workflow management. Evidence: Calls validate-yaml.py to verify YAML integrity in the manifest and documentation files. Evidence: Uses search-yaml.py to filter and manage documentation entries based on status. These tools are consistent with the skill's purpose and the author's development framework.

cs-libdoc