web-framework-angular-standalone
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a configuration schema at
https://raw.githubusercontent.com/agents-inc/cli/main/src/schemas/metadata.schema.json. This is a vendor-owned resource hosted on GitHub and is used for metadata validation. - [DATA_EXFILTRATION]: The code examples include usage of
fetchandHttpClientto communicate with local API endpoints (e.g.,/api/users). These are standard implementation patterns for the framework and do not exfiltrate sensitive data. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a reference for code migration and generation, which involves processing user-supplied source code. While this creates a theoretical surface for indirect prompt injection via code comments, the risk is mitigated as the skill does not grant the agent high-privilege capabilities such as arbitrary command execution or file system modification.
- Ingestion points: User-provided Angular code snippets and project structure (via
SKILL.mdand related examples). - Boundary markers: Standard Markdown headers and code blocks are used to delimit code.
- Capability inventory: No shell execution,
eval(), or sensitive file write capabilities are requested or used. - Sanitization: None specified, relying on platform-level LLM guardrails.
Audit Metadata