skills/openharmonyinsight/openharmony-skills/oh-distributed-security-design-review/Gen Agent Trust Hub
oh-distributed-security-design-review
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code for security reviews, which creates a surface for indirect prompt injection if the analyzed code contains hidden instructions.
- Ingestion points: Code snippets or files provided by the user during a review session in SKILL.md (Step 3).
- Boundary markers: None explicitly defined in the instructions to distinguish between the agent's logic and the untrusted code being analyzed.
- Capability inventory: The skill instructs the agent to perform text-based searches and generate review reports. It does not include commands for network access or file modifications.
- Sanitization: Not present.
- [SAFE]: The skill authored by 'openharmonyinsight' consists of legitimate security educational content and review workflows specific to the OpenHarmony ecosystem. The provided code examples and rules represent secure coding best practices and do not contain malicious payloads.
Audit Metadata