sequential-thinking
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Dynamic Execution (SAFE): The skill invokes a local script (
sequential-thinking.ts) using the Bun runtime. This is the intended core functionality and does not execute untrusted or remote code. - Indirect Prompt Injection (SAFE): The skill ingests text through the
--thoughtflag. - Ingestion points: Textual thoughts are passed as command-line arguments as seen in the
SKILL.mdusage examples. - Boundary markers: None identified in the provided script invocation examples.
- Capability inventory: The skill performs local script execution via the
bunruntime environment. - Sanitization: While no explicit sanitization is documented for the
--thoughtinput, the primary use case is internal agent reasoning, which minimizes the risk of adversarial input causing harm.
Audit Metadata