nist-csf-specialist
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted assessment data which presents a surface for indirect prompt injection.
- Ingestion points: The 'scripts/csf_maturity_assessor.py' tool reads organizational data from external JSON files via the '--input' parameter.
- Boundary markers: No explicit markers are used to delimit the tool output or warn the agent to ignore embedded instructions.
- Capability inventory: The skill possesses the capability to execute shell commands and perform file system read/write operations.
- Sanitization: No input validation or sanitization is performed on the 'evidence' or 'notes' fields of the provided assessment data.
- [COMMAND_EXECUTION]: The skill defines and instructs the agent to execute specific Python command-line tools ('scripts/csf_maturity_assessor.py' and 'scripts/csf_control_mapper.py') to perform its core functions.
Audit Metadata