report-writer
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands like
mkdir -pto prepare report directories andopen <path>to automatically launch the generated file in the default browser. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface because it retrieves and processes external content from vendor pages and communications.
- Ingestion points: External URLs, channel history, and local project documents.
- Boundary markers: The instructions do not define markers to isolate untrusted data within the generated HTML.
- Capability inventory: File system writes and local shell execution.
- Sanitization: No explicit sanitization or character escaping is required for the retrieved data before it is rendered in the HTML report.
Audit Metadata