sentry-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Sentry issue events, stack traces, and user tags) which could potentially contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: Data is ingested through tools such as
SENTRY_LIST_AN_ISSUES_EVENTSandSENTRY_RETRIEVE_AN_ISSUE_EVENTas described in SKILL.md. - Boundary markers: No explicit boundary markers or delimiters are defined to separate untrusted data from instructions, although the skill advises fetching the minimum data necessary.
- Capability inventory: The skill possesses write capabilities including creating alert rules (
SENTRY_CREATE_PROJECT_RULE_FOR_ALERTS), managing releases (SENTRY_CREATE_RELEASE_FOR_ORGANIZATION), and updating monitors (SENTRY_UPDATE_A_MONITOR). - Sanitization: The instructions recommend redacting exports/logs but do not provide specific mechanisms to prevent the agent from interpreting embedded text as instructions.
Audit Metadata