qinghu-pod-pattern-apply
Fail
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: HIGHPERSISTENCECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The skill recommends appending a path to
~/.bashrcto ensure the Node.js binaries remain in the environment'sPATHacross sessions. This modification of shell configuration files is a persistence mechanism. - [COMMAND_EXECUTION]: The skill utilizes shell commands like
curl,tar, andnpmfor installation, andsha256sumfor binary verification. These are used to set up theqhkitenvironment. - [EXTERNAL_DOWNLOADS]: Dependencies and binaries are fetched from trusted and well-known sources, including
nodejs.organd the Alibabanpmmirror.comregistry. - [CREDENTIALS_UNSAFE]: The instructions guide the user to set an API token via environment variables or CLI configuration commands. While no secrets are hardcoded, the skill is designed to handle sensitive authentication tokens.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through user-provided image paths and prompts in
SKILL.md. It uses a JSON-structured boundary for CLI parameters and has capabilities to execute local commands, but lacks explicit sanitization or filtering of the external input content.
Recommendations
- HIGH: Downloads and executes remote code from: https://nodejs.org/dist/v22.22.3/SHASUMS256.txt - DO NOT USE without thorough review
Audit Metadata