quarterly-connect

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted web search results, presenting a surface for indirect prompt injection.\n- Ingestion points: Web search for company core values (SKILL.md).\n- Boundary markers: None.\n- Capability inventory: No tools for file-system access or shell execution are present.\n- Sanitization: Summarization and user-confirmation steps mitigate risks.\n- [SAFE]: No malicious code or obfuscation was detected.\n- [NO_CODE]: The skill relies on prompt-based logic with no executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 11:49 AM