The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute commands using the twg CLI tool. It includes fallback logic to locate the executable in standard local directories such as $HOME/.local/bin/twg for macOS/Linux or the local app data folder for Windows if it is not present in the system PATH.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from several sources, creating a potential surface for indirect prompt injection.
Ingestion points: The agent is instructed to fetch and process Jira tickets, JSM incident records, meeting transcripts, and Slack conversation threads using tools like twg jsm incident query and twg jira workitem get.
Boundary markers: The skill does not provide specific instructions or delimiters to isolate untrusted data or warn the agent to ignore instructions embedded within the processed content.
Capability inventory: The skill utilizes the twg CLI for data retrieval across various Atlassian services and supports administrative mutations, such as updating Assets schema settings (twg assets objectschema settings update).
Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from tickets or transcripts before it is incorporated into the agent's context.

twg-operational-health