auto-industry-report
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided materials (files, search queries, and technical objects) to generate depth reports. This creates an attack surface for indirect prompt injection, where malicious instructions could be embedded in the source data to influence the report's output.
- Ingestion points: Processes user-provided materials, files, and search terms to populate report modules (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined in the skill body.
- Capability inventory: The skill generates offline HTML files and data visualizations using Chart.js; no dangerous command execution or network capabilities were found.
- Sanitization: The instructions do not define specific sanitization or filtering for external content, relying on the model's native safety protocols.
Audit Metadata