gridcraft

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and manipulate spreadsheet content, which creates a vulnerability to instructions embedded in cell values or formulas.
  • Ingestion points: Data enters the agent's context from workbooks via methods like sheet.read and cell.get, as documented in SKILL.md and references/control-protocol.md.
  • Boundary markers: No explicit markers or instructions are provided to help the agent distinguish between data and commands within spreadsheet content.
  • Capability inventory: The skill provides powerful tools including engine command execution, file system access, and UI automation, which could be misused if an injection occurs.
  • Sanitization: The skill lacks guidance on sanitizing or validating ingested data before it is used in subsequent agent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 05:38 PM