debugger
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is configured to use the
Bashtool as defined inreferences/agents/debugger.md. This allows the agent to execute arbitrary shell commands to diagnose and fix issues, which is a high-privilege capability. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and act upon untrusted external data.
- Ingestion points: The agent is explicitly instructed to analyze error messages, stack traces, and logs in
SKILL.mdandreferences/agents/debugger.md. - Boundary markers: There are no delimiters or instructions provided to the agent to treat input from logs or error messages as data rather than instructions.
- Capability inventory: The agent has access to
Bash,Edit,Read,Grep, andGlobtools, enabling it to modify the file system and execute code based on its analysis. - Sanitization: No sanitization or validation logic is specified to prevent the agent from obeying malicious instructions embedded in the logs it processes.
Audit Metadata