kids-online-safety-plan
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of purely instructional text to guide the AI agent in assisting users with children's safety plans. It does not include scripts, external dependencies, or command executions that could pose a risk to the environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data, including a child's age, devices, and parental concerns.
- Ingestion points: User inputs defined in the 'Required Inputs' section of SKILL.md.
- Boundary markers: The skill uses a structured output format but does not define explicit delimiters to isolate untrusted user data.
- Capability inventory: There are no capabilities present, such as tool invocation, file system access, or network operations.
- Sanitization: No explicit sanitization is defined for user-provided inputs.
- Conclusion: Because the skill lacks any actionable capabilities (e.g., shell execution or network access), this surface is not exploitable for system-level attacks.
Audit Metadata