spring-service
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided data directly into its instructions via the
$ARGUMENTSvariable. - Ingestion points: User input from the command invocation (e.g.,
/spring-service <Entity>) is inserted directly into the instruction body inSKILL.md. - Boundary markers: The template lacks delimiters or explicit instructions to treat the user-supplied entity name strictly as data, which could allow an attacker to attempt to override the skill's logic.
- Capability inventory: The skill is designed to create and modify source code files within the project (matching
**/*.java), which could be leveraged if an injection attack is successful. - Sanitization: There is no evidence of input validation or sanitization for the
$ARGUMENTSstring before it is processed by the model.
Audit Metadata