aeo-setup
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill captures user-provided information such as the company domain, company name, and list of competitors and interpolates these values directly into shell commands (e.g.,
npx goose-aeo init --domain <domain>). This presents an indirect command injection surface where malicious inputs containing shell metacharacters (like;,&&, or|) could lead to unauthorized command execution on the host system. - Ingestion points: User-provided domain, name, and competitors in SKILL.md Step 3.
- Boundary markers: None present; values are passed as raw flags.
- Capability inventory: Executes
npm run build,node,echo, andnpx goose-aeovia the Bash tool. - Sanitization: No explicit sanitization or validation of user-provided strings is performed before shell execution.
Audit Metadata