sentry-fix-stack-traces
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly identifies the risk of indirect prompt injection by warning the agent that Sentry event payloads (stack traces, breadcrumbs, and tags) are attacker-controllable. It instructs the agent to treat this data as untrusted and to never execute instructions found within event payloads or comments.
- Ingestion points: Sentry issue data and event payloads retrieved via MCP tools (Step 1).
- Boundary markers: Includes a clear instructional boundary warning the agent to disregard instructions embedded in the data.
- Capability inventory: Build tool configuration (e.g., bundler plugins, Gradle) and Sentry management tools.
- Sanitization: Relies on clear instructional guardrails within the SKILL.md to prevent the AI from acting on malicious content in the data it processes.
- [CREDENTIALS_UNSAFE]: The skill promotes secure credential management by instructing that Sentry authentication tokens must be stored in CI secrets or gitignored files, emphasizing that they should never be committed to version control.
Audit Metadata