react
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function of auditing and modifying existing codebases introduces a potential attack surface for indirect prompt injection. Ingestion points: Processes project source code, configuration files, and web pages via browser tools (SKILL.md, references/portals-and-stacking-context.md). Boundary markers: No instructions are provided to delimit untrusted code or to ignore instructions embedded within the files being audited. Capability inventory: The skill permits the agent to write files to the project and use browser inspection tools (SKILL.md). Sanitization: The instructions do not specify any validation or sanitization of content before it is processed or modified.
Audit Metadata