clerk-sms-logs
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
clerkCLI andcurlto interact with Clerk's Backend API for log retrieval. These commands are used for legitimate diagnostic purposes within the vendor's ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill processes log data from the Clerk API, creating a potential surface for indirect injection if the logs contain attacker-controlled strings.
- Ingestion points: API response payloads from
api.clerk.com/v1/logsas described in SKILL.md. - Boundary markers: Not present; the skill lacks explicit markers to differentiate between instructions and log data.
- Capability inventory: Execution of shell commands via the allowed Bash tool.
- Sanitization: The instructions do not prescribe sanitization of the retrieved log data.
Audit Metadata