The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill documentation includes an installation command curl -fsSL https://composio.dev/install | bash. This script originates from the vendor's domain and is used to establish the CLI environment required for the skill's operation.\n- [COMMAND_EXECUTION]: The skill uses the composio CLI to perform actions, including composio execute for API interactions and composio run for executing TypeScript-based automation scripts.\n- [EXTERNAL_DOWNLOADS]: The skill setup process involves downloading an installation script from the vendor's website.\n- [DATA_EXFILTRATION]: The skill is designed to transfer issue metadata between platforms such as Sentry, Linear, Jira, and Slack. This movement of data across external services is the intended purpose of the triage and sweep workflows.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes and acts on untrusted data from external issue trackers. \n
Ingestion points: Data enters the context from the Linear, Jira, and Sentry APIs (SKILL.md).\n
Boundary markers: Absent; the skill does not use delimiters to isolate external content.\n
Capability inventory: The skill can create or update issues, add comments, and send Slack messages (SKILL.md).\n
Sanitization: Absent; issue summaries and descriptions are interpolated directly into command arguments and message bodies.

issue-triage