team-web
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill serves as an orchestration template for managing web development tasks across specialized roles. It includes mandatory human-in-the-loop checkpoints via the AskUserQuestion tool at every phase transition, reducing the risk of autonomous unauthorized actions.- [PROMPT_INJECTION]: The skill processes user-provided feature descriptions and utilizes high-privilege tools such as Bash and Write. This creates a standard attack surface for indirect prompt injection where a malicious feature description could attempt to influence tool usage.
- Ingestion points: The [web feature description] argument in the YAML frontmatter.
- Boundary markers: Absent; user input is interpolated directly into the workflow context.
- Capability inventory: The skill is granted access to Bash, Task, Write, Edit, and Read tools.
- Sanitization: No explicit validation or sanitization of the input description is performed within the skill instructions.
Audit Metadata