cross-domain-seeing
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed strictly of markdown instructions and design principles. It does not contain any scripts, binary files, shell commands, or configuration that triggers code execution.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes conversation context and user-specified domains to extract design principles.
- Ingestion points: Processes the current conversation context and the
<domain>parameter as described inSKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted user input from the skill's logic.
- Capability inventory: None. The skill does not perform network operations, file system modifications, or command execution.
- Sanitization: No input validation or sanitization is present.
- Conclusion: While the skill ingests external data, it lacks the technical capabilities required for an injection attack to cause harm.
Audit Metadata