spring-boot-engineer
Fail
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: CRITICALMETADATA_POISONINGEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill metadata identifies the author as 'Jeffallan', which contradicts the provided developer context identifying the author as 'emmraan'. Such discrepancies in author attribution are characteristic of metadata poisoning or identity deception.
- [EXTERNAL_DOWNLOADS]: The documentation link (https://jeffallan.github.io/claude-skills/skills/backend/spring-boot-engineer/) is explicitly flagged by the URLite scanner as malicious. This URL points to a user-controlled GitHub Pages environment that is not associated with a verified or trusted organization.
- [COMMAND_EXECUTION]: The skill workflow requires the execution of Maven and Gradle wrappers (./mvnw and ./gradlew) to run tests. This creates a capability for the agent to execute shell commands, which could be exploited if instructions are influenced by malicious input.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted user requirements to generate code without using boundary markers or sanitization logic. 1. Ingestion points: Service requirement analysis in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Local command execution via build tool wrappers. 4. Sanitization: No filtering or escaping of external content is specified.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata