homelab-setup
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to manage a local hidden configuration file (~/.claude-homelab/.env). It uses sed -i for updates, echo for appending, and chmod 600 for permission management.
- [COMMAND_EXECUTION]: The skill executes a local shell script (setup-creds.sh) from a path constructed using environment variables or the user's home directory (${CLAUDE_PLUGIN_ROOT:-$HOME/claude-homelab}/scripts/setup-creds.sh).
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by interpolating user-supplied input (API keys, passwords, URLs) directly into shell commands without sanitization.
- Ingestion points: User responses containing credential values for services like Plex, Unifi, etc. in SKILL.md.
- Boundary markers: No explicit instructions are provided to sanitize or validate the user-provided strings before interpolation into shell commands.
- Capability inventory: The skill utilizes shell execution for file writing (sed, echo) and file permission modification (chmod) across all script segments.
- Sanitization: Sanitization is absent; the skill instructions suggest direct interpolation of user values (e.g., SERVICE_URL=$value) into strings executed by the shell.
Audit Metadata