The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Notion workspaces, which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The skill ingests external content via commands such as page get, database query, block children, and comment list in SKILL.md.
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when the agent processes retrieved Notion content.
Capability inventory: The skill possesses broad write capabilities (CRUD) within the Notion workspace, including creating/updating pages and appending blocks via the vibe-notionbot CLI.
Sanitization: There is no evidence of content sanitization or filtering for data retrieved from Notion before it is placed in the agent's context.
[EXTERNAL_DOWNLOADS]: The skill utilizes the vibe-notion package from the npm registry.
Evidence: The troubleshooting section in SKILL.md suggests running npx -y -p vibe-notion vibe-notionbot if the command is not found.
Context: The package is a vendor-owned resource associated with the skill author and represents standard installation behavior for this utility.

vibe-notionbot