viral-thread-generation
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill researches trending topics and competitor content by fetching external social media data, which introduces an indirect prompt injection surface where third-party content could influence the agent's behavior. Ingestion points: The skill uses x_search_tweets, x_get_tweets, and x_get_followers tools to ingest data (SKILL.md). Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the external data. Capability inventory: No subprocess calls, file-write operations, or dangerous shell commands were detected. Sanitization: No sanitization or filtering of the external content is described before it is used for generation.
Audit Metadata