ascend-mmcv-install
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches source code from the official OpenMMLab GitHub repository for manual compilation and installation.
- [COMMAND_EXECUTION]: Executes shell commands for repository cloning, package management via pip, and source compilation using python setup.py.
- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface by processing external files that could contain malicious instructions.
- Ingestion points: Reads requirements files and patch files from local paths (SKILL.md).
- Boundary markers: The skill does not implement delimiters or warnings to isolate external data from the agent's instruction context.
- Capability inventory: The agent has capabilities for command execution, repository cloning, and package installation.
- Sanitization: No validation or sanitization is performed on the content of the external patch or requirements files before they are processed.
Audit Metadata