skills/ozten/skills/find-bugs/Gen Agent Trust Hub

find-bugs

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes system commands (rm, mkdir, jq) and standard development tools (cargo, tsc, eslint, mypy) to manage a local analysis workspace and perform automated checks on user-provided code.\n- [PROMPT_INJECTION]: The skill processes untrusted source code from user-defined directories, creating an indirect prompt injection surface where embedded instructions could attempt to influence the behavior of the Search, Adversary, or Judge agents.\n
  • Ingestion points: Source files in the user-specified target directory (SKILL.md).\n
  • Boundary markers: No explicit delimiters or 'ignore' instructions are provided to separate user code from agent instructions.\n
  • Capability inventory: Local file system management (rm, mkdir), JSON manipulation (jq), and execution of external binaries (cargo, tsc, eslint, mypy).\n
  • Sanitization: No explicit sanitization or filtering of the ingested source code is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 05:10 AM