PDF Watermark

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected.
  • Ingestion points: PDF documents processed by the mcp tool add_watermark_to_pdf.
  • Boundary markers: No explicit markers or instructions are provided to the agent to ignore potentially malicious text embedded within the source PDF files.
  • Capability inventory: The skill leverages the office-mcp server tools to perform file system modifications and document generation.
  • Sanitization: The skill description does not specify sanitization or content filtering of the input PDF text before processing.
  • [NO_CODE]: The skill consists entirely of markdown documentation and YAML metadata. No executable scripts, binary files, or installation commands are present within the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:21 AM