csharp-client
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The SDK connection example demonstrates saving a session token to a plain text file named 'auth_token.txt' using
File.WriteAllText. Storing authentication credentials in unencrypted local files can lead to unauthorized access if the local environment is compromised. - [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for subscribing to and processing data from a SpacetimeDB instance, creating an attack surface for indirect prompt injection.
- Ingestion points: Data retrieved from external database tables through
SubscriptionBuilderand row-level event callbacks likeOnInsertandOnUpdate(SKILL.md). - Boundary markers: No specific delimiters or warnings are provided to instruct the agent to ignore instructions embedded within the database data.
- Capability inventory: The skill utilizes file system write capabilities (
File.WriteAllText) and standard console output. - Sanitization: There is no evidence of data sanitization, validation, or escaping of the content retrieved from the database before it is processed or displayed.
Audit Metadata