incident-lookup
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process untrusted data from external systems as part of its core functionality.
- Ingestion points: The skill retrieves content from Slack channels (
slack_search_public), Jira issues (searchJiraIssuesUsingJql), and GCP Cloud Logging (jsonPayload.message). - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between its system instructions and potentially malicious instructions embedded in the logs or messages it retrieves.
- Capability inventory: The agent possesses significant capabilities, including the ability to execute SQL queries on production BigQuery datasets and search production logs, which could be targeted by an indirect injection attack.
- Sanitization: No sanitization or validation logic is specified for the data retrieved from external tools before it is processed by the agent.
Audit Metadata