pencil-mcp-batch-get

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface through the ingestion of external file data.
  • Ingestion points: Data enters the agent's context via the filePath parameter and the subsequent retrieval of node properties from the specified file (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify any delimiters or safety markers to isolate the file content from the agent's instructional logic.
  • Capability inventory: The skill utilizes the batch_get tool (SKILL.md) which is capable of searching and reading properties of design nodes at various depths.
  • Sanitization: Absent; there is no evidence of validation or sanitization of the content being read from the external files.
  • [NO_CODE]: The skill does not contain any executable scripts, binaries, or compiled code, relying exclusively on markdown instructions and JSON tool configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:06 PM
Security Audit — agent-trust-hub — pencil-mcp-batch-get