java-architect

Fail

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL at https://jeffallan.github.io/claude-skills/skills/language/java-architect/ which has been flagged as malicious by reputation scanners. This link is embedded in the main documentation section of SKILL.md.
  • [COMMAND_EXECUTION]: The workflow instructions in SKILL.md direct the agent to execute shell commands such as ./mvnw verify and ./gradlew check. Executing scripts from a local project directory is dangerous if the project contains malicious wrapper scripts designed to perform unauthorized actions when called by the build tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external code and high-privilege capabilities.
  • Ingestion points: The agent reads and processes user-provided Java source code, pom.xml/build.gradle files, and project structures.
  • Boundary markers: Absent. The instructions do not provide delimiters or warnings to treat processed code as untrusted data, allowing instructions hidden in code comments or project files to potentially influence agent behavior.
  • Capability inventory: The skill has the capability to execute shell commands and read local files (e.g., JaCoCo reports).
  • Sanitization: Absent. There is no evidence of validation or sanitization of input data before it is used in command execution steps.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 6, 2026, 11:35 AM
Security Audit — agent-trust-hub — java-architect