The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute python scripts/supported_configurations.py. This script regenerates internal Python modules and performs validation checks against the current repository state.
[DYNAMIC_EXECUTION]: The skill triggers the regeneration of the ddtrace/internal/settings/_supported_configurations.py source file. This runtime modification of project code is driven by the data manually entered into supported-configurations.json.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect injection as it ingests user-supplied environment variable names, descriptions, and default values, which are then written to persistent project files and processed by the generation script.
Ingestion points: The agent is instructed to add user-provided data to supported-configurations.json and docs/configuration.rst.
Boundary markers: No specific delimiters or safety instructions are used to wrap the interpolated user content.
Capability inventory: The skill utilizes Edit for file modification and Bash for command execution, allowing the ingested data to potentially influence script behavior.
Sanitization: There is no evidence of sanitization, escaping, or schema validation for the input strings before they are written to disk.

add-new-configuration