Skills
Navigate
skills/pluginagentmarketplace/custom-plugin-java/java-testing-advanced/Gen Agent Trust Hub

java-testing-advanced

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided task descriptions without using explicit boundary markers or sanitization logic to isolate untrusted content.\n
  • Ingestion points: The skill ingests untrusted data via the 'technique' parameter in SKILL.md and user-defined task descriptions as described in references/GUIDE.md.\n
  • Boundary markers: There are no delimiters (like XML tags) or instructions to ignore embedded commands within the ingested data.\n
  • Capability inventory: The skill possesses powerful tools including Bash, Write, and Read as specified in the allowed-tools section of SKILL.md.\n
  • Sanitization: No input validation or sanitization routines are implemented for external data interpolated into the agent's context.\n- [COMMAND_EXECUTION]: The skill's configuration in SKILL.md allows the use of the Bash tool. While this tool is necessary for integration testing workflows (e.g., managing Testcontainers/Docker), it represents a functional capability that could be leveraged for arbitrary code execution if the agent is influenced by malicious input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:10 AM