Invoice Organizer

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes external data without sufficient safeguards.
  • Ingestion points: Data is ingested via extract_text_from_pdf and read_xlsx (SKILL.md).
  • Boundary markers: Absent; there are no delimiters to separate untrusted data from system instructions.
  • Capability inventory: The skill has the ability to write files using create_xlsx (SKILL.md).
  • Sanitization: Absent; no validation or sanitization is performed on the data extracted from files.
  • [NO_CODE]: The skill package does not contain any executable scripts or source code files, relying entirely on external MCP tools defined in the metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:18 AM