onboard
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform a best-effort connectivity test using a shell command (
ssh -o ConnectTimeout=5 ...). This command uses variables ($SSH_PORT,$SSH_USER,$HOST) that are populated directly from user input. Without explicit sanitization instructions, this configuration could allow for shell command injection if a user provides maliciously crafted connection strings. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a remote Synology NAS, which could lead to indirect prompt injection.
- Ingestion points: Data is retrieved from the output of
uname -aandcat /etc/synoinfo.confon the target NAS (SKILL.md, Step 3). - Boundary markers: No delimiters or instructions are provided to the agent to treat this remote output as untrusted or to ignore any instructions embedded within it.
- Capability inventory: The plugin has the ability to execute shell commands via SSH and write configuration files to the local filesystem (SKILL.md, Step 3 and 4).
- Sanitization: There is no specified sanitization or validation of the data returned from the remote SSH command before it is processed by the agent.
Audit Metadata