angular-developer

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [METADATA_POISONING]: The skill's metadata contains a copyright notice attributed to "Google LLC" and a future date (2026), which differs from the provided author context. This appears to be placeholder text or inherited boilerplate from official Angular templates.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to generate code based on user requirements and subsequently run terminal commands like ng build, ng test, and ng e2e to verify the output. This creates a surface where malicious instructions embedded in user input could be incorporated into the project and executed during the build or test phase.
  • Ingestion points: User-provided project requirements and component logic definitions (processed in SKILL.md).
  • Boundary markers: None explicitly defined for isolating generated code blocks from the agent's instructions.
  • Capability inventory: The skill facilitates terminal execution of ng build, ng test, ng e2e, and ng serve (referenced in cli.md and mcp.md).
  • Sanitization: No specific sanitization or validation of the generated code is described before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:52 AM
Security Audit — agent-trust-hub — angular-developer