The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from multiple external sources.
Ingestion points: Fetches content from a Notion calendar (Step 1), reads related project files or notes (Step 2), and retrieves existing blog posts via MCP (Step 2).
Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore instructions found within the ingested data.
Capability inventory: The skill has the ability to execute shell commands (git commit), call MCP tools for post creation (create_post), interface with social media schedulers, and modify the Notion calendar.
Sanitization: There is no evidence of validation or sanitization of the data retrieved from Notion or local files before it is used to generate content or influence logic flow.
[COMMAND_EXECUTION]: The skill utilizes local shell commands to manage a git repository.
Evidence: Executes git add and git commit -m to stage and commit generated blog articles (Step 5). These commands are restricted to the content/blog/ directory and appear intended for the primary purpose of the skill.

write-article