spark-recipe-shared-inbox-status
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard workflows for auditing shared inboxes using vendor-specific CLI tools. All commands listed are consistent with the read-only access level specified in the metadata.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute
sparkCLI commands to retrieve account information, email lists, and team workload summaries. - [INDIRECT_PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection by instructing the agent to read external email content.
- Ingestion points: Reading email thread content via the
spark thread <id>command as mentioned in the Tips section. - Boundary markers: None present; the skill does not explicitly instruct the agent to ignore instructions embedded within the retrieved emails.
- Capability inventory: Access to the
sparkCLI which can read email data, team structures, and account details. - Sanitization: None present; the skill relies on the underlying platform's handling of tool outputs.
Audit Metadata