The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes content retrieved from external Notion databases and pages which can serve as a vector for indirect prompt injection if those sources contain malicious instructions.
Ingestion points: Page and block content retrieval via api.notion.com endpoints.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided templates.
Capability inventory: The skill has access to shell command execution (curl, jq) and local file system writes in /tmp.
Sanitization: No explicit filtering or sanitization of retrieved block text is performed before it is handled by the agent context.
[COMMAND_EXECUTION]: Executes system commands including curl, jq, echo, and tr to perform API operations and format identifiers. This is required for the skill's functionality.
[DATA_EXFILTRATION]: Retrieves the NOTION_TOKEN from environment variables and transmits it to the official Notion API (api.notion.com) for authentication. This is standard behavior for an API integration and targets a well-known service domain.
[SAFE]: No obfuscation, unauthorized privilege escalation, or persistence mechanisms were detected. The skill correctly identifies its required secrets in the metadata and directs all network requests to established service providers.

notion