debug-tools
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell-based grep commands to locate and verify the removal of debug logs in the project codebase. It also suggests using available debugging tools like Chrome DevTools and Console Ninja for runtime inspection.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it analyzes project source code to identify root causes and suggest fixes. It lacks explicit instructions for the agent to use boundary markers or delimiters when processing untrusted code content, which could lead the agent to follow instructions embedded in comments or strings within the analyzed files.\n
- Ingestion points: Project source files and error logs analyzed during the investigation and pattern comparison phases.\n
- Boundary markers: Absent; there are no defined delimiters to separate analyzed data from agent instructions in the provided references.\n
- Capability inventory: The skill has file read/write access and the ability to execute shell commands for code analysis.\n
- Sanitization: Absent; the skill does not specify procedures for sanitizing or escaping instructions that may be embedded in the data it processes.
Audit Metadata