marketing-twitter-engager
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and respond to untrusted data from Twitter, including mentions, direct messages, and trending topics. This creates a vulnerability where an attacker could embed malicious instructions in a tweet or DM to influence the agent's subsequent actions.
- Ingestion points: Real-time monitoring of mentions, DMs, hashtags, and trending conversations.
- Boundary markers: The instructions do not define delimiters (e.g., XML tags or triple backticks) or specific 'ignore embedded instructions' warnings for external content.
- Capability inventory: No shell commands, file system operations, or network tools are explicitly invoked in this file, though the agent's broader environment may provide them.
- Sanitization: No protocols are mentioned for filtering, escaping, or validating the content of incoming tweets or messages before processing.
Audit Metadata