twitter-check
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of Twitter mentions, which could contain malicious instructions designed to influence the agent's auto-response logic or behavior.
- Ingestion points: Recent @mentions are fetched via the
twitter-mcpserver (SKILL.md). - Boundary markers: The workflow does not explicitly mention the use of delimiters or 'ignore embedded instructions' prompts when processing the fetched mention text.
- Capability inventory: The skill has write capabilities, specifically the ability to post replies and heartbeat tweets to Twitter via the
twitter_heartbeat_cycletool (SKILL.md). - Sanitization: No explicit sanitization or filtering of the tweet content is described in the workflow before it is used to generate responses.
Audit Metadata