The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands including tar for creating backups of documentation and runs project-specific Python scripts such as scripts/extract_tags.py and scripts/validate_tags_against_docs.py to perform validation tasks.
[PROMPT_INJECTION]: Indirect prompt injection surface identified:
Ingestion points: The skill scans and parses artifacts and source code in the docs/, src/, and tests/ directories.
Boundary markers: No explicit delimiters or instructions are used to separate untrusted parsed content.
Capability inventory: The skill has the ability to execute shell commands and write to the local file system.
Sanitization: There is no mention of sanitizing or validating the extracted content before it is used to generate reports or modify files.

trace-check