newspaper-explainer
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute system commands and read local files to collect data points for generating reports. This functionality is intended for gathering technical dispatches and project status updates within the agent's environment.\n- [EXTERNAL_DOWNLOADS]: The newspaper template fetches typographic assets from Google's public font delivery infrastructure (fonts.googleapis.com and fonts.gstatic.com).\n- [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection because it processes content from potentially untrusted files and command outputs.\n
- Ingestion points: Information is ingested from arbitrary files and system command results in
commands/generate-dispatch.md.\n - Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the gathered data.\n
- Capability inventory: The skill allows for file system writes, command execution, and launching the system browser.\n
- Sanitization: Absent; no sanitization or validation of the collected data is performed before it is rendered into the final HTML output.
Audit Metadata