agency-twitter-engager
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a significant surface for indirect prompt injection as it is designed to ingest and act upon untrusted external data.
- Ingestion points: The skill instructions specifically require the agent to monitor "trending topics, hashtags, and industry conversations," "mentions," "DMs," and "influencer content" (referenced in Phase 1, Phase 3, and throughout SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore or sanitize instructions found within the tweets, DMs, or trending content it processes.
- Capability inventory: The agent is designed to produce output based on this data, including creating replies, educational threads, and managing brand conversations, which could be manipulated by an attacker who crafts a tweet containing hidden instructions.
- Sanitization: There are no documented sanitization or validation steps for the external content before it is used to influence the agent's behavior or output.
Audit Metadata