tree-of-thought
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is restricted to natural language instructions and templates for structured reasoning. No scripts, binaries, or executable code are included.
- [EXTERNAL_DOWNLOADS]: The README file references the author's GitHub repository (github.com/synapseradio/) for installation instructions and license information. These references are consistent with standard vendor resource usage.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user input.
- Ingestion points: User input is ingested via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: None identified.
- Capability inventory: No subprocess calls, execution commands, file-write operations, or network tools are present in the skill files.
- Sanitization: No sanitization or filtering is applied to the input content.
Audit Metadata