interactive-content
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill includes defensive instructions against indirect prompt injection, specifically stating that submitted user answers must be treated as material/data and never as commands.
- [DATA_EXFILTRATION]: No exfiltration patterns detected. The skill explicitly forbids the harvesting of sensitive personal data (health/finance) through casual interactive features and requires consent before sharing user responses.
- [EXTERNAL_DOWNLOADS]: The skill mentions industry reports from well-known sources (Buffer, Meta) as references for engagement statistics, but does not perform any automated downloads or script executions.
- [COMMAND_EXECUTION]: No unauthorized or dangerous command execution patterns detected. The skill describes tool boundaries for 'WoopSocial', noting it cannot perform certain native platform actions.
- [SAFE]: The skill demonstrates high awareness of platform safety and ethical guidelines, including compliance with contest laws and human-in-the-loop requirements for native platform features.
Audit Metadata