saleor-security
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data which could potentially contain malicious instructions that influence its behavior.
- Ingestion points: The skill utilizes WebSearch to query for authentication flows and security headers, and WebFetch to retrieve content from the Saleor developer documentation.
- Boundary markers: There are no defined delimiters or instructions provided to explicitly ignore instructions embedded within the retrieved data.
- Capability inventory: The skill allows the use of Write, Edit, and Bash tools, which gives the agent the ability to modify the project environment based on information fetched from the web.
- Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from external searches or documentation fetches before it is applied to the application configuration.
Audit Metadata