The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the official CLI installation script from the vendor's developer domain (cli.sentry.dev) and pipes it to bash. This is the standard, vendor-recommended installation method and is considered safe given the skill's origin.\n- [COMMAND_EXECUTION]: Instructs the agent on how to use the sentry command-line tool for managing projects, issues, and organizations. The skill includes commands for initialization, release management, and dashboard configuration.\n- [DATA_EXFILTRATION]: Includes commands like sentry auth token which expose sensitive authentication credentials to the terminal output. While this reveals sensitive data, it is a legitimate administrative function of the CLI.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it retrieves and analyzes potentially untrusted external data (Sentry issues, logs, and traces) using AI-powered analysis tools like sentry issue explain.\n
Ingestion points: Data retrieved from Sentry APIs via commands like sentry issue view, sentry log list, and sentry span list (documented in SKILL.md and references/issues.md).\n
Boundary markers: No explicit delimiters or instructions are provided to the agent to isolate or ignore embedded instructions within the fetched data.\n
Capability inventory: The agent has access to powerful CLI operations, including sentry api for arbitrary network requests and destructive operations like sentry project delete.\n
Sanitization: There is no indication of sanitization or validation of external content before it is processed by the AI agent.

sentry-cli