nist-csf-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the skill's instructions and Python scripts revealed no security issues. The scripts follow standard patterns for local data processing and report generation without external dependencies or network calls.
- [INDIRECT_PROMPT_INJECTION]: The skill features a surface for indirect prompt injection because it processes user-provided assessment data.
- Ingestion points: User-supplied JSON data is ingested via the
--inputflag inscripts/csf_maturity_assessor.py. - Boundary markers: The skill does not use specific delimiters to isolate user-provided evidence and notes in the generated Markdown reports.
- Capability inventory: The skill's capabilities are limited to local file I/O for reading inputs and writing reports; it does not possess network, subprocess, or dynamic code execution capabilities.
- Sanitization: No sanitization is performed on input strings before they are formatted into the final reports.
Audit Metadata