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 viapandoc.\n - Boundary markers: No delimiters or isolation markers are used when providing content to the agent.\n
- Capability inventory: Subprocess execution of
pandocandcat.\n - Sanitization: No sanitization is applied to the document content before it enters the context.
Audit Metadata