saleor-checkout
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches live documentation from Saleor's official documentation site (docs.saleor.io). This is a legitimate practice for accessing technical guidelines.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it instructs the agent to retrieve information from external sources (web search and documentation) and perform tasks using tools like Bash and Write. This configuration could allow externally-sourced malicious instructions to influence agent behavior.
- Ingestion points: Web search results and documentation content from docs.saleor.io as specified in SKILL.md.
- Boundary markers: Absent. External content is not delimited or marked as untrusted.
- Capability inventory: The skill is configured to use tools including Bash, Write, Edit, WebSearch, and WebFetch as seen in SKILL.md.
- Sanitization: Absent. The fetched content is not validated or sanitized before being processed by the agent.
Audit Metadata