nano-pdf

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'nano-pdf' package via PyPI. This is a standard dependency for the skill's functionality but involves downloading external code from a public registry.
  • [DATA_EXFILTRATION]: The skill transmits PDF data to an external API endpoint (https://api.opencclaw.com/nano-pdf/extract) for processing. While this is the intended primary purpose of the skill, users should be aware that sensitive document content is sent to a third-party service.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it extracts and mines text from PDFs, which are external, untrusted data sources.
  • Ingestion points: Reads and processes PDF files through 'extract' and 'mine' commands.
  • Boundary markers: There are no explicit delimiters or warnings mentioned to prevent the agent from following instructions embedded within the extracted PDF text.
  • Capability inventory: The skill has the capability to perform network requests (via the 'requests' library) and execute local commands (via the 'nano-pdf' binary).
  • Sanitization: The documentation does not specify any sanitization, filtering, or validation of the extracted text before it is returned to the agent or used in subsequent operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:44 PM