sentry-fix-stack-traces
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from Sentry event payloads (such as frame paths, exception text, and breadcrumbs). It explicitly instructs the agent to treat this data as attacker-controllable and never execute any instructions found within the payloads. This demonstrates a strong security-first design for handling external data.
- [CREDENTIALS_SAFE]: The documentation provides clear guidance on the secure management of
SENTRY_AUTH_TOKEN. It advises against committing tokens to source control and recommends using CI secrets or gitignored environment files. It also provides a method to verify the presence of a token without exposing its value. - [EXTERNAL_DOWNLOADS]: The skill references official tools provided by Sentry, such as
sentry-cliand@sentry/wizard, which are standard utilities for the intended functionality and are downloaded from well-known package registries.
Audit Metadata