lean-grill
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, command executions, or external dependencies were detected. The skill consists entirely of instructional markdown and a standard MIT license.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as requirements and plans, which introduces a theoretical surface for indirect prompt injection.\n
- Ingestion points: The skill accepts an "existing requirement, scope or plan" as input in
SKILL.md.\n - Boundary markers: No specific delimiters are defined to isolate external project data from the skill's instructions.\n
- Capability inventory: The skill does not request or define capabilities for file writing, network access, or shell command execution.\n
- Sanitization: No validation or sanitization logic is present to filter or escape untrusted input content.
Audit Metadata