context-loader

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands (pandoc, cat) to manipulate and read filesystem data.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external file content.\n
  • Ingestion points: Hidden Word documents (.*.docx) are read via pandoc.\n
  • Boundary markers: No delimiters or isolation markers are used when providing content to the agent.\n
  • Capability inventory: Subprocess execution of pandoc and cat.\n
  • Sanitization: No sanitization is applied to the document content before it enters the context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:58 AM
Security Audit — agent-trust-hub — context-loader