entry-sheet-review
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, command injection, or unauthorized network activities were detected in the skill instructions or the provided Python script.
- [DATA_EXPOSURE]: The skill processes sensitive resume data but includes logic in
scripts/check_entry_sheet.pyto detect and flag contact details (emails, phone numbers). The instructions explicitly direct the agent to propose their removal from the text body to prevent accidental exposure. - [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for untrusted user drafts. However, the risk is mitigated by a mandatory evidence classification system (confirmed vs. reported) and a rigid report structure. The accompanying Python script performs only structural and regex-based analysis, ensuring input text is not executed.
- [COMMAND_EXECUTION]: The skill uses a local script
scripts/check_entry_sheet.pyfor text analysis. Analysis of the source code confirms it uses only Python standard libraries and performs no dangerous system calls or file writes.
Audit Metadata