The Agent Skills Directory

[SAFE]: No malicious patterns, such as obfuscation, credential exfiltration, or unauthorized network access, were found. The skill's behavior is consistent with its stated purpose of building development artifacts.- [COMMAND_EXECUTION]: The skill defines a command that executes a local script (role-compile.ps1 or role-compile.py) provided within the skill package. These scripts process user-provided JSON data to generate XML files and register them in the Configuration.xml file. These operations are restricted to the local file system paths provided by the user.- [PROMPT_INJECTION]: The skill processes untrusted JSON data which presents a surface for indirect prompt injection.
Ingestion points: The JsonPath parameter allows the agent to read and process external JSON files.
Boundary markers: None. The skill does not provide specific instructions to the agent to treat the JSON content purely as data.
Capability inventory: The skill has the capability to write XML files to the local disk and modify the configuration of a 1C:Enterprise project.
Sanitization: The scripts perform XML entity escaping on content derived from the JSON input to ensure the generated files are well-formed and to prevent basic injection into the XML structure.

role-compile