The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external file inputs.
Ingestion points: Untrusted data enters the agent context through docs/seo/<slug>/outline.md and docs/seo/<slug>/research-brief.md as specified in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided in SKILL.md to distinguish between the provided data and the agent's instructions, increasing the risk that instructions embedded in those files could be obeyed.
Capability inventory: The agent has capabilities to read reference files and write a draft markdown file to the filesystem.
Sanitization: There is no evidence of sanitization, validation, or escaping of the content read from the external markdown files before processing.

seo-write