sentry-fix-stack-traces
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection when processing untrusted data from Sentry issue details and event payloads. Ingestion points: Event data retrieved via MCP tools (
search_issues,get_issue_details) inSKILL.md. Boundary markers: Explicit instructions to treat MCP output as untrusted and never execute instructions found within payloads. Capability inventory: Configuring build tools and executing vendor CLI tools (Sentry Wizard). Sanitization: Relies on agent following instructions to ignore embedded commands. - [COMMAND_EXECUTION]: The skill references standard vendor-provided tools and build tool configurations to upload debug artifacts.
- [CREDENTIALS_UNSAFE]: The skill provides best-practice guidance for handling authentication tokens, instructing that they should be stored in CI secrets or gitignored files rather than committed to version control.
Audit Metadata