vps-service-status
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell command execution via SSH to perform system diagnostics. It uses placeholders like
<vps-host>,<service>, and<port>which are intended to be replaced with user-supplied values. If the agent does not properly sanitize these inputs, it could lead to command injection on the local system running the agent. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests and processes untrusted data from remote sources.
- Ingestion points: Service logs retrieved via
docker compose logs, container statuses fromdocker ps, and HTTP response bodies fromcurlhealth probes. - Boundary markers: None identified. The skill does not instruct the agent to use delimiters or ignore instructions found within the retrieved data.
- Capability inventory: Local shell execution (
ssh), clipboard access (pbcopy), and file system navigation. - Sanitization: There is no evidence of output sanitization or filtering before the agent processes the retrieved text.
- [DATA_EXFILTRATION]: While serving a legitimate diagnostic purpose, the skill retrieves and transmits server-side information (process lists, disk usage, memory stats, and application logs) from a remote VPS into the agent's local context.
Audit Metadata