hipaa-compliance-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's documentation and requirements involve downloading NLP models from spaCy, a well-known service. These downloads are standard for the tool's NLP functionality.
- [COMMAND_EXECUTION]: The skill requires manual execution of Python and shell commands for setup and auditing (e.g.,
python -m spacy download,python scripts/main.py). These commands are standard for the intended use case and do not trigger unauthorized actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted clinical text, which constitutes an ingestion surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the context via the
--textand--inputparameters inscripts/main.py. - Boundary markers: There are no explicit delimiters or boundary markers used to isolate the input text from processing instructions.
- Capability inventory: The skill's capabilities are limited to local file system reads and writes (via
scripts/main.py), with no network operations or dynamic code execution found. - Sanitization: The script provides PII redaction and de-identification but does not include generic escaping or sanitization for subsequent LLM processing.
Audit Metadata