The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The documentation uses placeholders like sk_YOUR_API_KEY and sk_your_api_key to explain how to configure API authentication. No hardcoded or sensitive credentials are exposed in the skill.
[EXTERNAL_DOWNLOADS]: The skill utilizes an MCP server hosted at mcp.publora.com. This is a vendor-owned domain used to provide the skill's core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for social media posting, which is its primary purpose.
Ingestion points: content parameter within the create_post tool in SKILL.md.
Boundary markers: None defined; the tool relies on the agent's context to provide the intended input.
Capability inventory: Executes network requests to the Publora API to publish content externally.
Sanitization: The skill documentation indicates that text is automatically split and formatted server-side by the Publora platform.

threads-post