sota-jvm

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit and process external, untrusted codebases. This creates a surface for indirect prompt injection where malicious instructions embedded in the audited code (e.g., in comments or strings) could attempt to deceive the agent or manipulate its audit findings.\n
  • Ingestion points: The agent reads various source code files (.java, .kt), build files (pom.xml, build.gradle), and configuration files from the project directory.\n
  • Boundary markers: The skill provides structured audit checklists and finding formats to keep the agent focused, but does not include explicit markers to ignore instructions within the content of the files being scanned.\n
  • Capability inventory: The skill facilitates extensive filesystem read access and the execution of local shell commands (grep, find, awk) for pattern matching.\n
  • Sanitization: File contents are processed via regular expressions; there is no sanitization of the input data before it enters the agent's context for analysis.\n- [COMMAND_EXECUTION]: The audit checklists provided in the skill rely on the execution of complex shell commands (using utilities like grep, find, awk, sed, xargs, and git). These commands are used to identify security anti-patterns in the local codebase. While these are legitimate tools for the skill's purpose, they demonstrate a reliance on shell logic execution in the agent's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 10:22 AM