need-explorer
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines an alias SSF that invokes node on a local script path: "/scripts/spec-superflow.mjs". This tool is used to record milestone confirmations via shell command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill provides shell command templates that incorporate user-supplied variables: SSF state set dp_1_result "confirmed: ". 1. Ingestion points: User-provided text for the summary and change directory are used to construct CLI commands. 2. Boundary markers: While double quotes are used in the template, there is no guidance for the agent to sanitize shell metacharacters or escape nested quotes. 3. Capability inventory: The skill possesses command execution capabilities via the Node.js runtime. 4. Sanitization: The instructions lack requirements for input validation or sanitization before interpolation into shell commands.
Audit Metadata