accelerate-python-resolvers
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python diagnostic script,
accelerator-diagnostics.py, which evaluates the project's code for static acceleration compatibility. - [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files and Python source code, creating a surface for indirect instructions. Ingestion points: Python resolver functions and project configuration files like
chalk.yaml. Boundary markers: The instructions do not specify any explicit boundary markers or delimiters for the ingested code. Capability inventory: Execution of local Python scripts within the project environment. Sanitization: No specific sanitization or filtering of the ingested project content is mentioned. - [SAFE]: The skill facilitates authentication with the official vendor service at
https://accelerator.chalk.aivia theCHALK_ACCELERATOR_TOKENenvironment variable, which is a standard practice for this service.
Audit Metadata