trade-report-pdf

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the terminal to discover files (ls -la TRADE-*.md) and execute a localized Python script (python3 ~/.hermes/skills/trade/scripts/generate_trade_pdf.py) to process data and generate the report.
  • [EXTERNAL_DOWNLOADS]: The skill attempts to install the reportlab package from the standard Python package registry if it is not already installed on the system.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files which could potentially contain untrusted content.
  • Ingestion points: The skill reads all markdown files in the current directory matching the pattern TRADE-*.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions within the trade analysis files.
  • Capability inventory: The skill utilizes terminal access for file operations, package installation, and script execution.
  • Sanitization: Data is parsed into a structured JSON format before being passed to the PDF generator, providing a layer of structural validation, though text content is not explicitly sanitized.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 AM
Security Audit — agent-trust-hub — trade-report-pdf