ssh-dev-suite/debug
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute a wide range of system commands on remote servers and within containers (Docker). While standard diagnostic commands like
top,df, andnetstatare listed, the instructions also allow for 'deep troubleshooting' by executing arbitrary commands based on interpreted clues. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources which presents an indirect injection risk.
- Ingestion points: The agent reads system logs (
journalctl), application logs in/var/log/,docker logs, and local engineering files to infer dependencies. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or sanitize embedded instructions found within the logs or file content.
- Capability inventory: The skill possesses extensive command execution capabilities via the
connect/scripts/ssh-exec.shscript, including system configuration checks, file reading, and network utility execution. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from remote logs before it is processed by the agent's logic.
Audit Metadata