The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download a standalone Python script (dsp-cli.py) from an external GitHub repository (k-kolomeitsev/data-structure-protocol) using curl. This source is not associated with a recognized trusted organization or well-known service.
[REMOTE_CODE_EXECUTION]: Following the download, the skill executes the script using the local Python interpreter (python dsp-cli.py ...). This 'fetch-and-execute' pattern from an unverified source allows for arbitrary code execution on the user's host system.
[COMMAND_EXECUTION]: The skill relies on shell command execution to perform its core functions. It passes project paths and metadata as arguments to the dsp-cli.py script, which could be exploited if the script or the agent does not properly sanitize these inputs.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8).
Ingestion points: The skill reads project source code, including developer comments (e.g., // @dsp func-...), and processes them via dsp-cli.py.
Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed code files.
Capability inventory: The skill has the capability to execute shell commands and write to the local file system (creating the .dsp/ directory).
Sanitization: There is no evidence of sanitization or validation of the content extracted from the source code before it is used to generate the structural graph or passed to the CLI tool.

data-structure-protocol