adobe-anyexcel
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of user-provided PDF files, which introduces a potential surface for indirect prompt injection from data embedded within those documents.
- Ingestion points: The skill instructions specifically mention handling source content from uploaded or attached PDF files.
- Boundary markers: The skill does not provide the agent with specific delimiters or instructions to treat the PDF content as untrusted data or to disregard potential instructions hidden within the text and tables of the source document.
- Capability inventory: The skill utilizes the
pdf_exporttool for automated conversion and references standard data processing libraries such asopenpyxlandpandas. - Sanitization: No explicit sanitization, validation, or filtering procedures for the extracted PDF data are defined within the skill's instructions.
Audit Metadata