saleor-testing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches configuration files from the official Saleor project repository on GitHub.
- Evidence: Instruction to fetch
https://github.com/saleor/saleor/blob/main/conftest.pyto review test configuration. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external sources and process it using file modification and execution tools.
- Ingestion points: The agent is directed to use
WebFetchto retrieve files from GitHub andWebSearchto gather Saleor documentation and fixture patterns. - Boundary markers: Absent. There are no explicit instructions to treat the fetched content as data rather than instructions or to delimit it from the system prompt.
- Capability inventory: The skill permits the use of
Write,Edit, andBashtools, which could be used to act upon instructions found in the external data. - Sanitization: Absent. No validation or filtering is specified for the content retrieved from the web or GitHub before it is processed by the agent.
Audit Metadata