scr
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, prompt injections, or unauthorized data access patterns were identified. The skill instructions focus entirely on logical message construction.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context to generate message drafts. While this is an ingestion surface, the risk is minimal as the skill lacks access to sensitive data or executable tools. 1. Ingestion points:
SKILL.mdinstructions for processing 'supplied context'. 2. Boundary markers: Absent. 3. Capability inventory: Text generation only; no subprocesses or network operations. 4. Sanitization: Absent.
Audit Metadata