excalidraw-diagram
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were detected in the instructions.
- [DATA_EXFILTRATION]: No network operations, sensitive file access, or hardcoded credentials were found. The skill operates entirely within the context of generating diagram data.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or packages. References to external services like excalidraw.com are strictly informational.
- [COMMAND_EXECUTION]: No shell commands or system-level operations are included in the skill's workflow.
- [OBFUSCATION]: The content is clear and uses no encoding techniques, hidden characters, or homoglyphs to mask malicious intent.
- [CREDENTIALS_UNSAFE]: No API keys, tokens, or private secrets are present in the files.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied descriptions, it lacks any dangerous capabilities (like file writes or network access) that could be exploited via malicious input.
Audit Metadata