react-hook-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by processing untrusted user input while having access to high-privilege tools.
- Ingestion points: Processes user requests containing keywords like 'react hook creator', 'react creator', and the broad term 'react' as specified in the description and triggers.
- Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to isolate user-provided data from the agent's logic.
- Capability inventory: The skill is granted unrestricted access to file operations (Read, Write, Edit) and shell command execution (Bash with cmd:*) via the frontmatter allowed-tools field.
- Sanitization: No explicit input validation, escaping, or sanitization mechanisms are defined to mitigate the risk of malicious instructions within processed data.
Audit Metadata