check-releases

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill provides documentation and examples for a Sentry release monitoring tool. It uses existing Sentry MCP tools for data retrieval and does not contain any executable code, remote downloads, or credential exposure.
  • [PROMPT_INJECTION]: The skill processes external data from Sentry (error messages, issue titles) which presents a surface for indirect prompt injection.
  • Ingestion points: SKILL.md describes fetching release health metrics and issue details from Sentry.
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore embedded commands in the Sentry data.
  • Capability inventory: The skill utilizes Sentry MCP tools to list releases and fetch metrics.
  • Sanitization: None mentioned. The model is expected to analyze raw error data directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:23 AM
Security Audit — agent-trust-hub — check-releases