doc-type-classifier
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill performs keyword-based classification of document content.
- [COMMAND_EXECUTION]: The skill provides a CLI script for classification, but it only performs read-only operations on the specified input file.
- [DATA_EXPOSURE]: While the skill reads local file content, it does so to perform classification. There are no network operations or external endpoints present to facilitate data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted document content, but its logic is restricted to basic string inclusion checks and keyword counts, which poses no risk of instruction override or capability exploitation.
Audit Metadata