related-skill
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party packages from the inference.sh registry.
- Evidence: Multiple instructions to use
npx skills addto fetch and integrate additional modules from an external source. - [REMOTE_CODE_EXECUTION]: Enables the execution of remote code by adding new skills to the agent's active environment.
- Evidence: The skill's primary function is to trigger the download and execution of external skill definitions to extend capabilities.
- [PROMPT_INJECTION]: The discovery workflow interacts with an external registry, creating a surface for indirect prompt injection from remote skill descriptions.
- Ingestion points: Search results and list outputs from the
npx skillscommand. - Boundary markers: No explicit delimiters or instructions are provided to the agent for handling registry data.
- Capability inventory: The skill can execute subprocesses to install and update additional software.
- Sanitization: No input validation or sanitization of registry output is documented.
Audit Metadata