backend-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted code snippets provided by users, which constitutes an indirect prompt injection surface.
- Ingestion points: Java/Kotlin source code provided by the user for review.
- Boundary markers: Absent. The prompt instructions do not provide specific delimiters or ignore-instructions to isolate the code being analyzed from the agent's logic.
- Capability inventory: None. The skill does not have access to file writing, network requests, or system command execution; it only produces text-based feedback.
- Sanitization: Absent.
- [No Code] (SAFE): The skill contains no executable code files (.py, .js, .sh) or automation scripts. It consists entirely of YAML frontmatter and Markdown instructions.
- [Data Exposure] (SAFE): No hardcoded credentials, API keys, or sensitive file paths were detected in the instructions.
- [External Downloads] (SAFE): No remote scripts or external dependencies are downloaded or executed by this skill.
Audit Metadata