The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of arbitrary shell commands through the asc workflow run command, which reads from a repository-local configuration file.- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to malicious instructions embedded in the .asc/workflow.json file.
Ingestion points: The skill reads workflow definitions from .asc/workflow.json within the project directory.
Boundary markers: The documentation contains safety rules advising users to only run trusted workflow files and avoid untrusted pull requests.
Capability inventory: The skill can execute shell commands and handle environment variables via the asc CLI tool.
Sanitization: No command sanitization is mentioned for the content of the workflow JSON.

asc-workflow