The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill attempts to install the desloppify Python package from the public PyPI registry. The package is sourced from a personal GitHub repository (peteromallet/desloppify), which is not associated with a verified or trusted organization.
[COMMAND_EXECUTION]: The skill utilizes shell commands to install software (pip install) and execute the desloppify command-line tool. These commands run with the permissions of the agent and can perform sweeping modifications to the codebase.
[PROMPT_INJECTION]: The skill implements a codebase scanning and fixing loop that processes local file content. This creates an indirect prompt injection surface where the agent's actions (such as determining the next fix or applying changes) could be manipulated by malicious instructions or data embedded within the files being analyzed.
Ingestion points: Reads files from the local directory during the desloppify scan and desloppify next steps.
Boundary markers: The instructions do not define delimiters or specific warnings for the agent to ignore instructions embedded in the analyzed code.
Capability inventory: Includes shell execution for package installation and file-system-altering CLI commands.
Sanitization: There is no evidence of sanitization or validation of the data retrieved from the codebase before it is used to determine agent actions.

desloppify