qinghu-shipinhao-share-link
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download Node.js binaries and checksum files from nodejs.org and its official mirrors to set up the execution environment.
- Evidence: Installation steps in SKILL.md use
curlto fetch tarballs and SHASUMS from nodejs.org. - [COMMAND_EXECUTION]: The skill relies on the execution of the
qhkitCLI tool for its core functionality, including managing service configuration and calling MCP tools. - Evidence: Instructions describe using
qhkit mcp call,qhkit config set, andqhkit config showto perform tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data returned by the
qhkittool, which could potentially contain malicious instructions if the upstream data source is compromised. - Ingestion points: The agent reads the JSON output from
qhkit mcp call(SKILL.md). - Boundary markers: Output is restricted to a single-line JSON format.
- Capability inventory: The skill can execute shell commands via the
qhkitCLI and read local files for large datasets. - Sanitization: No explicit sanitization or escaping of the tool output is mentioned in the instructions.
Audit Metadata