disclosure-check
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external analysis output files (logs, tables, CSVs), creating a surface for indirect prompt injection if those files contain adversarial content.
- Ingestion points: Processes multiple file formats including .tex, .csv, .log, and .out from a user-defined outputs directory.
- Boundary markers: The skill does not implement explicit delimiters or warnings to ignore instructions within the processed data files.
- Capability inventory: Employs Read, Grep, Glob, Write, and Bash tools to perform the analysis and generate reports.
- Sanitization: The instructions lack specific guidance for sanitizing or escaping content extracted from input files before it is placed into the final Markdown report.
Audit Metadata