kepner-tregoe-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied technical data (e.g., concern descriptions, IS/IS NOT specifications, and decision criteria) which is then processed by Python scripts to generate JSON analysis files and HTML reports.
- Ingestion points: The four rational processes (Situation Appraisal, Problem Analysis, Decision Analysis, and Potential Problem Analysis) all rely on interpolating user input into structured analysis data.
- Boundary markers: The SKILL.md file includes explicit instructions for the agent to treat user-provided text as data rather than instructions, though these are advisory and do not prevent adversarial injection.
- Capability inventory: The skill utilizes scripts (calculate_scores.py, generate_report.py, score_analysis.py) that perform local file read and write operations within the agent environment.
- Sanitization: The generate_report.py script implements HTML character escaping (via html.escape) when generating report content to mitigate cross-site scripting risks in the resulting documentation.
Audit Metadata