The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the twg command-line tool to perform deep searches and fetch content from various enterprise applications. Commands include twg rovo search, twg confluence content get, and twg jira workitem get. This is standard functionality for interacting with the vendor's Teamwork Graph and Rovo services.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as Slack messages, Google Drive documents, and GitHub repositories. This creates a surface for indirect prompt injection. However, the skill provides specific rules to treat snippets as candidates rather than facts and requires verification across multiple primary sources, which mitigates the risk of the agent following malicious instructions embedded in the processed data.

twg-agentic-search