sentry
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate set of tools for interacting with Sentry's API. No obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were found.
- [EXTERNAL_DOWNLOADS]: The skill communicates with
https://mcp.sentry.dev/mcp, which is an official Sentry developer domain for MCP integrations. This is documented and aligns with the skill's purpose. - [DATA_EXFILTRATION]: Authentication tokens are stored in the user's home directory at
~/.mcp-skill/auth/. This is a standard practice for local agent skills to persist sessions and does not represent an exfiltration risk. - [PROMPT_INJECTION]: Tool descriptions and hints (e.g., in
search_issuesandget_issue_details) provide guidance to the model on how to correctly choose and use tools. These are helpful operational instructions rather than malicious overrides or bypasses.
Audit Metadata