platform-rest-client
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reviews and refactors user-provided Java/Spring code, creating a surface where malicious instructions embedded in the input source could influence the agent's output behavior.
- Ingestion points: The agent ingests user-provided Java source code, Maven configuration files (pom.xml), and application properties during refactoring tasks described in
SKILL.md. - Boundary markers: The instructions lack specific delimiters or instructions for the agent to treat user-provided code as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill allows the agent to generate new code, modify existing project files, and suggest configuration changes across the application.
- Sanitization: There are no explicit validation or sanitization steps defined for the external code content before it is processed by the agent.
Audit Metadata