spring-kotlin-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to analyze untrusted external data, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads changed files, diffs, tests, and build configuration files (e.g.,
SKILL.mdspecifies reading diffs, controllers, services, and migrations). - Boundary markers: There are no instructions providing delimiters or 'ignore embedded instructions' warnings to prevent the agent from following instructions hidden within the code it is reviewing.
- Capability inventory: While the skill's own instructions do not invoke dangerous tools, it operates in an environment where the agent may have access to the file system or network, which could be exploited if an injection succeeds.
- Sanitization: The instructions do not include any steps for escaping or validating the external content before the agent processes it.
Audit Metadata