specsfy-specialist-debian-server
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain malicious instructions.
- Ingestion points: The agent reads system state through commands like 'cat /etc/os-release', 'systemctl --failed', and 'journald' logs as part of its diagnostics flow (SKILL.md, references/standards.md).
- Boundary markers: No explicit delimiters or 'ignore' instructions are used when processing server output.
- Capability inventory: The skill has the capability to execute shell commands, manage services, and write to system configuration files (e.g., '/etc/sysctl.d/', 'ansible/inventory.yml').
- Sanitization: There is no mention of sanitizing or escaping the data read from the server before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill directs the agent to perform high-privilege system administration tasks.
- Evidence: Instructions include creating a new 'deploy' user, configuring 'sudo' permissions, and modifying system-level files like 'sshd_config', 'nftables.conf', and kernel parameters in '/etc/sysctl.d/'. These actions are consistent with the skill's stated purpose of server preparation and hardening.
Audit Metadata