hot-topics
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill has a surface for indirect prompt injection as it ingests untrusted data from external sources via the
search_viewpointstool. 1. Ingestion points: Data from YouTubers processed viasearch_viewpoints. 2. Boundary markers: Absent. 3. Capability inventory: Limited to information retrieval; no file-writing or network-exfiltration tools detected. 4. Sanitization: Absent. - [NO_CODE] (SAFE): The skill consists exclusively of markdown instructions and metadata, with no provided scripts or executable binaries, which eliminates risks from malicious code or dependency vulnerabilities.
Audit Metadata