weekly-aeoncard
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
render_card.pyexecutes thersvg-convertsystem utility viasubprocess.runto rasterize generated SVG cards. The execution uses a defined argument list and system-derived file paths. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local token usage logs and git metadata.
- Ingestion points: Reads activity data from
memory/token-usage.csvand git remote details. - Boundary markers: The summary data is interpolated into notification messages without explicit delimiters.
- Capability inventory: The skill can write files to the output directory, execute local binaries, and send notifications.
- Sanitization: The skill utilizes an
esc()function to escape HTML/SVG special characters before rendering content, mitigating potential injection risks in visual artifacts.
Audit Metadata