The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and rewrite user-supplied prose, which creates a potential surface for indirect prompt injection. \n- Ingestion points: Target files specified by the user or found in content/posts/*.md (Workflow section). \n- Boundary markers: The instructions do not define clear delimiters or 'ignore' instructions for the content being processed. \n- Capability inventory: The skill uses a local script (scripts/style_scan.py) to read files and employs subagents to rewrite files in place. \n- Sanitization: There is no mention of escaping or validating the content of the prose drafts before processing.

writing-axes