resume-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill contains no attempts to override system instructions or bypass safety filters. Instructional markers like 'IMPORTANT' and 'CRITICAL' are appropriately used to guide the agent through task-specific constraints such as LaTeX preamble management and document sizing.\n- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive system paths (e.g., credentials or SSH keys) and does not perform any network operations that could exfiltrate data.\n- [Indirect Prompt Injection] (LOW): The skill processes untrusted input from an external tool. \n
- Ingestion points: Data provided by the
ExperienceSelectortool is interpolated into LaTeX templates.\n - Boundary markers: None identified.\n
- Capability inventory: Uses
create_latex_file(file write) andcompile_pdf(local execution of the LaTeX compiler via the MCP server).\n - Sanitization: The skill provides an explicit list of special characters to escape (
&,%,$,#,_) to prevent compilation crashes and basic injection.\n- [Command Execution] (SAFE): The skill relies on structured MCP tools rather than arbitrary shell access. It explicitly warns the agent against manual shell commands (e.g.,mkdir), reducing the risk of unintended command execution.
Audit Metadata