money-product
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill refers users to
ccapi.aifor acquiring Gemini API keys when they are not present in the environment. The skill instructions include a disclosure that this service is operated by the skill suite's author. - [COMMAND_EXECUTION]: The skill is designed to perform extensive system operations, including initializing projects with frameworks (Next.js, FastAPI, Expo), managing version control via git, and executing deployments via CLI tools for Vercel and Railway. These operations are core to the skill's stated purpose of building and shipping products.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads and incorporates content from files within the project repository to guide its execution logic.
- Ingestion points: Reads
DESIGN.md,CHANGELOG.md,VERSION, and~/.smtm/projects/{slug}/profile.jsonto determine architectural decisions, versioning, and design constraints. - Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore malicious commands embedded within these files.
- Capability inventory: File system modification (code generation, config writing), network operations (API interactions, deployment), and shell command execution (deployment tools, build scripts).
- Sanitization: Absent; no explicit validation or filtering of the content read from the project files is described.
Audit Metadata