decision-toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources, such as meeting transcripts and personal notes, as outlined in the 'Gather Context' step in
SKILL.md. This data is then interpolated into placeholders within HTML and Markdown templates.\n - Ingestion points: Meeting transcripts, notes, and user-provided background information specified in
SKILL.md(Step 1).\n - Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers to isolate untrusted data during the generation process.\n
- Capability inventory: The skill produces interactive HTML files containing JavaScript (using
templates/decision-guide-template.html) which include user-controlled content.\n - Sanitization: No sanitization, escaping, or validation logic is specified in the skill instructions to prevent malicious strings in the input from being rendered as executable code in the output.\n- [DYNAMIC_EXECUTION]: The skill generates interactive tools (HTML/JS) and structured records (Markdown) by dynamically populating predefined templates with user-supplied content. While this is a standard feature for generating customized decision tools, it represents a dynamic content generation pattern that depends on the integrity of the input data.
Audit Metadata