inspecting-angular-apps
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates the inspection of Angular applications using a dedicated CLI tool (ng-agent). The operations are focused on retrieving diagnostic information from local development environments (localhost) and do not involve unauthorized network communication or data exfiltration.\n- [PROMPT_INJECTION]: The skill is designed to ingest data from a running Angular application, which is a potential surface for indirect prompt injection. This is a characteristic of tools that read external application state.\n
- Ingestion points: Runtime inspection commands such as ng-agent snapshot, ng-agent query, and ng-agent signals list in SKILL.md.\n
- Boundary markers: The skill instructs the agent to distinguish between observed, instrumented, and inferred relations, which helps in contextualizing data, though no explicit data delimiters are used.\n
- Capability inventory: The skill enables read-only diagnostic commands. Runtime mutations are disabled by default, requiring a local token for any changes.\n
- Sanitization: No explicit sanitization or filtering of the ingested application data is described.
Audit Metadata