yao-kelly-skill
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external JSON briefs to calculate allocation strategies and render HTML reports, creating a surface where malicious instructions could be embedded in the data.
- Ingestion points: Data is read from user-specified file paths by
scripts/kelly_allocation_report.pyandscripts/generate_html_report.py. - Boundary markers: The processing logic lacks explicit markers or instructions to isolate untrusted data from the agent's execution context.
- Capability inventory: The skill has the ability to write result files and reports to the filesystem.
- Sanitization:
scripts/generate_html_report.pyuseshtml.escape()for all values interpolated into the final HTML artifact, mitigating typical injection risks in the output.
Audit Metadata