country-cv-format
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of user-provided CVs, creating a surface for potential indirect prompt injection.
- Ingestion points: The skill accepts a "current CV" as a required input, which is then processed to generate a formatted version.
- Boundary markers: No explicit delimiters or boundary markers (e.g., XML tags or specific separators) are used to isolate the user-provided CV content from the skill's instructions.
- Capability inventory: The skill is restricted to text generation and formatting. It does not have access to tools for network communication, file system operations, or shell command execution.
- Sanitization: No sanitization or escaping of the CV content is performed before processing.
- Conclusion: While the surface exists, the lack of powerful tools or capabilities makes the risk of a malicious CV hijacking the agent for harmful purposes negligible.
Audit Metadata