shopware-cli-extension-store
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute vendor-provided shopware-cli commands (e.g., extension validate) to audit local extensions for store compliance.
- [EXTERNAL_DOWNLOADS]: The skill references official Shopware developer documentation (developer.shopware.com) as the authoritative source for its classification table and compliance guidelines.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local extension files and CLI tool output, creating a potential surface for indirect prompt injection.
- Ingestion points: composer.json, src/Resources/config/config.xml, and the stdout stream of the shopware-cli validation command.
- Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or ignore embedded instructions when reading these data sources.
- Capability inventory: The skill has the capability to execute shell commands (via shopware-cli) and read/write files in the extension root.
- Sanitization: Absent. However, the skill mitigates this risk by enforcing a highly rigid response structure and explicit emission rules that constrain the agent to a predefined classification table, preventing the agent from following instructions embedded in the audited content.
Audit Metadata