kieran-typescript-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review code changes, which serves as a vector for indirect prompt injection if the ingested code contains malicious instructions.
- Ingestion points: Code blocks, React components, and TypeScript modules provided by the user for review in the agent's context (referenced in SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore prompt injection attempts within the code being reviewed.
- Capability inventory: The skill contains natural language instructions for code review; it does not explicitly define subprocess calls or network operations in this file.
- Sanitization: There is no evidence of sanitization or filtering of the input code to prevent the agent from executing instructions hidden within code comments or strings.
Audit Metadata