twitter-automation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) as it is designed to ingest and process untrusted data from Twitter via search and lookup functions. This is inherent to its primary purpose as a social media automation tool. Ingestion points: Data enters the agent context through tools like TWITTER_RECENT_SEARCH, TWITTER_FULL_ARCHIVE_SEARCH, and TWITTER_POST_LOOKUP_BY_POST_ID mentioned in SKILL.md. Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings when the agent processes retrieved content. Capability inventory: The skill allows creating posts (TWITTER_CREATION_OF_A_POST) and deleting posts (TWITTER_POST_DELETE_BY_POST_ID). Sanitization: There is no evidence of sanitization or filtering of the content retrieved from Twitter before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill interacts with the Rube MCP service via https://rube.app/mcp and refers to composio.dev for documentation, both of which are recognized service providers for AI toolkits.
Audit Metadata