why
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external sources including Slack, Notion, and Git. Ingestion points: Data is pulled from various external sources described in the source playbooks. Boundary markers: Prompt templates lack explicit instructions to ignore malicious content within fetched data. Capability inventory: The environment provides shell access via git and gh and database query capabilities. Sanitization: No explicit sanitization or validation is performed on the ingested content before synthesis.
Audit Metadata