list-machines

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script (scripts/list-machines.sh) from a hardcoded directory: /home/daniel/repos/github/my-repos/Claude-Security-Auditor-Plugin.
  • [COMMAND_EXECUTION]: User-provided inputs (machine name and view flags) are passed directly as arguments to the bash script. This creates a command injection surface if the underlying script does not properly sanitize these arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a vulnerability surface for indirect prompt injection by ingesting and processing untrusted machine metadata.
  • Ingestion points: Fleet metadata files read by the list-machines.sh script (SKILL.md).
  • Boundary markers: None provided in the instructions to delimit metadata from instructions.
  • Capability inventory: Execution of shell scripts via bash.
  • Sanitization: No sanitization or validation of the ingested metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:15 PM
Security Audit — agent-trust-hub — list-machines