pencil-mcp-batch-get
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes node data and properties from Pencil files, which represents an attack surface for instructions hidden within design assets to influence the agent.
- Ingestion points: Output from the
batch_gettool in SKILL.md and referenced example configurations. - Boundary markers: The skill does not provide delimiters or negative constraints to prevent the agent from following instructions embedded in the design nodes.
- Capability inventory: The skill provides structural and property information to the agent, which can drive logic for subsequent tool use.
- Sanitization: No sanitization or validation of the retrieved node properties is mentioned or implemented in the skill instructions.
Audit Metadata