aem-cli
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process content from local folders and remote AEM pipelines, which introduces a potential surface for indirect prompt injection.
- Ingestion points: The skill utilizes the
--html-folderflag to serve local HTML files and the--urlflag to proxy content from remote AEM pipeline URLs. - Boundary markers: There are no specific instructions or delimiters provided to ensure the agent ignores potentially malicious instructions embedded within the ingested data.
- Capability inventory: The skill facilitates local web server operations, network requests to external pipelines, and synchronization of content with da.live.
- Sanitization: No sanitization or validation protocols for the external content are mentioned in the skill instructions.
- [COMMAND_EXECUTION]: The skill provides standard instructions for installing and executing the
@adobe/aem-clitool. - Evidence: Installation via
npm install -g @adobe/aem-cliand execution via commands such asaem up,aem import, andaem contentare documented as standard usage patterns for this vendor tool.
Audit Metadata