Twitter Engager
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to monitor and respond to real-time external data, creating an attack surface for instructions embedded in third-party content.
- Ingestion points: The agent is instructed to monitor brand mentions, Direct Messages (DMs), and trending industry conversations (SKILL.md).
- Boundary markers: Absent. There are no explicit instructions for the agent to distinguish between valid data and malicious instructions embedded in those inputs.
- Capability inventory: While the skill documentation does not list specific tools, its core mission (replying to tweets/DMs and posting content) implies write-access to social media APIs.
- Sanitization: Absent. The skill lacks guidance on sanitizing or escaping content retrieved from external conversations before processing.
Audit Metadata