kuikly-ui-framework
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to clone the KuiklyUI repository from GitHub to the local environment.
- Evidence:
- URL: https://github.com/Tencent-TDS/KuiklyUI
- File: SKILL.md
- Mechanism: The agent is instructed to use 'git clone' if the directory is missing.
- [COMMAND_EXECUTION]: The skill relies on shell command execution to maintain its reference documentation and repository state.
- Evidence:
- The agent is instructed to run 'mkdir', 'cd', and 'git clone' in SKILL.md.
- The agent is instructed to execute local bash scripts: 'scripts/check-update.sh' and 'scripts/update-repository.sh'.
- [INDIRECT_PROMPT_INJECTION]: The skill consumes external data from a git repository to fulfill user requests, which could lead to instruction overrides if the external content is compromised.
- Evidence:
- Ingestion points: The agent reads documentation and source code from 'references/KuiklyUI/docs/' and 'references/KuiklyUI/core/'.
- Boundary markers: Missing. No delimiters or instruction-ignore warnings are specified for reading these files.
- Capability inventory: The skill has shell execution capabilities (bash, git, filesystem operations).
- Sanitization: Absent. There is no evidence of content filtering or validation before the agent processes the retrieved text.
Audit Metadata