skills/aeonfun/aeon/weekly-aeoncard/Gen Agent Trust Hub

weekly-aeoncard

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill's Python script (render_card.py) uses subprocess.run to invoke the rsvg-convert system utility for SVG-to-PNG conversion. This execution is confined to a specific utility using templated, local file paths and does not facilitate arbitrary command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local ledger (memory/token-usage.csv). It implements proper XML escaping (sanitizing '&', '<', '>') for all values extracted from the CSV before embedding them into the SVG image, effectively preventing injection attacks or malformed artifact generation from untrusted ledger entries.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses internal token usage telemetry to generate reports and visualizations. The data is processed locally, and the resulting summaries are sent via a local notification script. No sensitive credentials or private files are accessed or transmitted.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 06:38 PM
Security Audit — agent-trust-hub — weekly-aeoncard