The Agent Skills Directory

[DYNAMIC_EXECUTION]: The script scripts/validate.py uses the compile() function to perform syntax checks on the skill's own Python scripts. This is a local validation step used to ensure code integrity before execution and does not involve running untrusted code strings.
[DYNAMIC_EXECUTION]: The scripts scripts/parse_docs.py and scripts/scan_tools.py utilize __import__ to load the standard library datetime module.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from a target repository's files (YAML frontmatter and Markdown content) and includes it in generated reports, creating a vulnerability surface for indirect prompt injection.
Ingestion points: scripts/scan_tools.py parses YAML frontmatter from SKILL.md files; scripts/parse_docs.py parses Markdown content from various README files.
Boundary markers: The generated reports do not use specific delimiters or warnings to isolate the extracted tool descriptions from the rest of the agent's context.
Capability inventory: The skill has access to powerful tools including Bash, Read, Write, and Edit.
Sanitization: Extracted strings (such as tool names and descriptions) are interpolated directly into the markdown report without sanitization or escaping.

docs-sync-checker