react-best-practices
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of analyzing external codebase content.
- Ingestion points: The skill uses
Read,Grep, andGlobtools to ingest untrusted data from the user's local React components, hooks, and test files (e.g., inreferences/testing-quality.md). - Boundary markers: Absent. There are no instructions directing the agent to use delimiters or ignore instructions that may be embedded in comments, strings, or metadata within the analyzed source code.
- Capability inventory: The skill utilizes high-privilege tools including
Bash,WebFetch,Write, andEdit, which could be abused if the agent is manipulated by instructions hidden in the code it audits. - Sanitization: Absent. No specific validation, escaping, or filtering processes are defined for the data read from the codebase before it is processed by the agent.
- [SAFE]: References and documentation links target the author's own official repository (
somnio-software/somnio-ai-tools), which is consistent with the skill's intended purpose and provider identity.
Audit Metadata