spring-java-reviewer
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of untrusted source code.\n
- Ingestion points: The skill workflows in
SKILL.mdinstruct the agent to use globbing (src/main/java/**/*.java) and file-reading tools to ingest project source code into its context.\n - Boundary markers: The prompt instructions do not specify any delimiters (such as XML tags or markdown blocks) or safety instructions to separate the source code content from the analysis logic, potentially allowing code comments to be interpreted as agent instructions.\n
- Capability inventory: The skill utilizes filesystem tools (
Read,Glob) to access and process data from the project directory.\n - Sanitization: There are no sanitization steps, such as filtering or escaping, performed on the input source code before it is processed by the agent.
Audit Metadata