The Agent Skills Directory

[PROMPT_INJECTION]: The skill requires the agent to inspect repository source files, configuration, and tests to replace template content with project-specific facts. This creates an indirect prompt injection surface where malicious content embedded in the analyzed codebase could attempt to influence the agent's behavior or the resulting documentation.
Ingestion points: SKILL.md procedure step 1 (Inspect the repository, existing documentation, configuration, and relevant source files).
Boundary markers: Absent; the instructions do not specify the use of delimiters or provide warnings to ignore instructions embedded within the source data.
Capability inventory: The skill possesses file-writing capabilities via scripts/init_docs.py and the ability to generate repository content.
Sanitization: Absent; there is no mention of filtering or sanitizing content derived from the project files before it is incorporated into the documentation.
[COMMAND_EXECUTION]: The skill executes scripts/init_docs.py, a bundled Python script, to create the documentation directory structure and initial files. The script uses standard libraries to perform local file system operations without network interaction or external dependency requirements.

harness-docs-init