pdf-convert

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external PDF and Markdown files, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in the documents.\n
  • Ingestion points: Untrusted data enters the agent context through to-pdf/scripts/lib/config-loader.cjs (via loadMarkdown) and to-markdown/scripts/lib/converter.cjs (via convertNative using @opendocsg/pdf2md).\n
  • Boundary markers: The conversion process does not appear to use specific boundary markers or "ignore instructions" warnings when presenting converted content to the agent.\n
  • Capability inventory: The skill possesses the ability to write to the file system (e.g., fs.writeFileSync in to-markdown/scripts/lib/converter.cjs) and spawn child processes (spawnSync in scripts/convert.cjs).\n
  • Sanitization: There is no evidence of content sanitization or instruction filtering applied to the extracted text before it is returned to the agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:42 PM