women-ai-topic-radar
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a transparent research assistant, focusing on content curation and report generation. It uses standard file operations within its own documentation directory and does not exhibit any patterns of privilege escalation or persistence.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes untrusted content from social media platforms (Xiaohongshu, Weibo, WeChat, and X/Twitter). 1. Ingestion points: Social media signal collection (SKILL.md, references/source-playbook.md). 2. Boundary markers: Strict adherence to structured templates (references/report-template.md) and scoring dimensions (references/scoring-rules.md). 3. Capability inventory: Retrieval of social signals and writing markdown files to a local 'docs/women-ai-topic-radar/' directory. 4. Sanitization: The multi-step transformation process—filtering by audience lens and expanding into specific topic angles—prevents the agent from executing instructions found within the processed social data.
Audit Metadata