remote-compute-ssh

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill does not contain malicious code or deceptive instructions. It outlines a standard operational workflow for remote compute management.
  • [PROMPT_INJECTION]: The skill is designed to ingest remote job logs and output into the agent workspace, which introduces a potential surface for indirect prompt injection if the remote data contains adversarial instructions.
  • Ingestion points: Harvesting of stdout, stderr, and job logs from remote SSH/Slurm hosts into the workspace (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the ingested content.
  • Capability inventory: The skill facilitates remote job submission, SSH host access, and artifact synchronization.
  • Sanitization: No explicit sanitization or content validation steps are defined for the harvested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:04 AM
Security Audit — agent-trust-hub — remote-compute-ssh