The Agent Skills Directory

[SAFE]: The skill operates as a template orchestrator, generating structured work items for various project management tools based on user-provided configuration. It uses established platform integrations (MCP servers and official CLI tools like gh and az) to perform its intended functions.
[PROMPT_INJECTION]: The skill ingests user input (such as team names and project keys) and interpolates them directly into templates and search queries (JQL, WIQL). While this creates a potential surface for indirect prompt injection or query manipulation, the risk is inherent to the tool's core purpose as a templating engine and is considered safe within the context of project management automation. The use of standard placeholders {{token}} provides clear boundary markers for the interpolation.
[COMMAND_EXECUTION]: The skill is designed to interact with external tools to create and manage tickets. The commands used (e.g., gh issue create, az boards work-item create) are documented, transparent, and aligned with the skill's stated purpose. There is no evidence of arbitrary or malicious command execution.
[EXTERNAL_DOWNLOADS]: All external references and documentation links point to official vendor domains (pactflow.io, pact.io) or well-known trusted services (github.com), following safe development practices.

contract-testing-flywheel