temp-email
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes use of shell commands including curl, jq, and grep to perform API requests and process data.
- [DATA_EXFILTRATION]: The skill performs network operations to api.tempmail.lol to manage temporary inboxes and retrieve message content.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Data is ingested from external email bodies via the tempmail.lol API (SKILL.md).
- Boundary markers: The skill does not provide explicit instructions or delimiters to the agent to ignore or isolate instructions found within the email content.
- Capability inventory: The skill uses curl, jq, and grep to retrieve and parse data, providing a vector for processing untrusted content.
- Sanitization: No sanitization or validation is applied to the incoming email content before processing.
Audit Metadata