db-core/mutations-optimistic
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data via optimistic actions and mutation handlers, which represents a potential attack surface for indirect prompt injection if the ingested data contains malicious instructions.\n
- Ingestion points: Untrusted data enters the agent context through the
variablesparameters inonMutateandmutationFndefinitions withinSKILL.md.\n - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided code examples.\n
- Capability inventory: The skill utilizes network operations (via
apicalls) and collection updates (collection.insert,collection.update,collection.delete) within its scripts and examples inSKILL.md.\n - Sanitization: The provided examples do not demonstrate explicit input validation, escaping, or sanitization of the external data before it is used in database or network operations.\n- [EXTERNAL_DOWNLOADS]: The skill references the
@tanstack/dbpackage and several modules within it. These are official resources from the skill author and do not indicate a security risk.
Audit Metadata