am-i-drifting
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on ingesting two sets of five posts provided by the user for analysis. These samples constitute untrusted data. The instructions lack explicit boundary markers or sanitization steps to prevent the agent from accidentally executing instructions hidden within the user-pasted text.
- [COMMAND_EXECUTION]: The documentation outlines the use of specific tools including
get_voice_insights,list_posts, andget_analyticswhen connected to the VoiceMoat service. These tools facilitate the retrieval and analysis of external data from social media platforms like Twitter and LinkedIn.
Audit Metadata