devops
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local infrastructure inventory files such as .agent-devops.env to determine server targets and configuration. This data ingestion acts as a potential surface for indirect prompt injection.
- Ingestion points: The skill reads server names, IP addresses, and SSH settings from environment files.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded in these files.
- Capability inventory: The skill possesses powerful capabilities including remote command execution via SSH and cloud resource provisioning via provider CLIs.
- Sanitization: There are no instructions for sanitizing or validating inventory values before they are interpolated into shell commands.
- [COMMAND_EXECUTION]: The skill performs shell-based operations to interact with cloud provider CLIs (hcloud, doctl, linode-cli, etc.) and to verify server connectivity. These commands are consistent with the skill's stated purpose of remote infrastructure administration.
Audit Metadata