The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with Azure DevOps REST API endpoints. All commands are constructed within the user's environment and target the legitimate dev.azure.com domain.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch configuration and data from Azure DevOps services. These operations target the official dev.azure.com domain, which is a well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided input for project and team names which are interpolated into shell commands. This attack surface is mitigated by explicit instructions requiring the agent to URL-encode these names and escape shell-sensitive characters like the dollar sign ($).
Ingestion points: User-provided project, team, and iteration names in SKILL.md.
Boundary markers: The skill instructs the agent to ask for missing information and perform validation through specific API calls.
Capability inventory: Shell execution via curl for reading and writing iteration data.
Sanitization: Mandatory URL encoding for paths and specific escaping for query string parameters.
[SAFE]: The skill implements secure credential management by sourcing authentication tokens (AZURE_DEVOPS_PAT, AZURE_DEVOPS_TOKEN) exclusively from environment variables. It contains explicit prohibitions against requesting users to provide secrets in plain text or logging them to the file system.

work-iterations