The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it is designed to ingest and process untrusted content from Twitter.
Ingestion points: Untrusted data enters the agent context through tools such as TWITTER_RECENT_SEARCH, TWITTER_FULL_ARCHIVE_SEARCH, and TWITTER_POST_LOOKUP_BY_POST_ID as described in SKILL.md.
Boundary markers: The instructions lack delimiters or specific directives for the agent to ignore instructions embedded within the retrieved tweet content.
Capability inventory: The skill has the ability to perform impactful actions on the external platform, including TWITTER_CREATION_OF_A_POST and TWITTER_POST_DELETE_BY_POST_ID.
Sanitization: No sanitization, escaping, or validation logic for external content is specified in the workflows.
[EXTERNAL_DOWNLOADS]: The skill configuration requires the addition of an external MCP server endpoint (https://rube.app/mcp) to interface with the Twitter API.

twitter-automation