local-pdf-editor

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts including pdf_utils.py and safe_copy.py via shell commands to process user files.
  • [PROMPT_INJECTION]: The skill processes content from untrusted PDF files, creating a surface for indirect prompt injection attacks where malicious instructions in a document could influence agent behavior.
  • Ingestion points: User-provided PDF documents are ingested and analyzed from the input/ directory.
  • Boundary markers: There are no explicit instructions or delimiters defined to prompt the agent to ignore or isolate instructions found within the PDF text content.
  • Capability inventory: The skill environment supports subprocess execution of scripts and web-based research capabilities.
  • Sanitization: The instructions do not specify any validation or sanitization of text extracted from the PDF files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 12:43 AM
Security Audit — agent-trust-hub — local-pdf-editor