skill-health
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script using the path
${CLAUDE_PLUGIN_ROOT}/scripts/health.mjs. This involves a subprocess call to thenoderuntime using environment variables for path resolution. - [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing external data.
- Ingestion points: User input is accepted via
$ARGUMENTSand passed to the shell command. The output of the script is then returned to the agent. - Boundary markers: There are no boundary markers or delimiters defined to isolate the script's output from the agent's instruction set.
- Capability inventory: The skill has the capability to execute JavaScript files locally via Node.js.
- Sanitization: There is no evidence of sanitization for the input arguments or the resulting script output, which the agent is explicitly told not to modify or summarize.
Audit Metadata