investigate-sentry-issue
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Sentry error reports, including stacktraces, breadcrumbs, and tags, which could contain adversarial instructions aimed at influencing the agent's behavior.
- Ingestion points: Error data and metadata are retrieved from Sentry REST API endpoints (e.g.,
/api/0/organizations/and/events/recommended/) as described inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to treat ingested error content as untrusted data, increasing the risk of the agent following embedded instructions.
- Capability inventory: The skill utilizes the
sentry-clito perform actions such as listing, resolving, and muting issues, which could be abused if an injection is successful. - Sanitization: There is no evidence of filtering or sanitizing the content of exceptions or breadcrumbs before they are analyzed by the agent.
Audit Metadata