syncing-migrated-self-managed-tables
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources via tools like
external-data-schemas-retrieveandexternal-data-schemas-list. - Ingestion points: Untrusted data enters the agent context through schema metadata and error messages (
latest_error) retrieved from the PostHog data warehouse API (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing these tool outputs.
- Capability inventory: The skill utilizes tools to modify schema configurations (
external-data-schemas-partial-update) and initiate data synchronizations (external-data-schemas-reload) (SKILL.md). - Sanitization: No explicit sanitization or validation of the retrieved metadata or error strings is described.
Audit Metadata