audit-clerk-skill
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones the Clerk CLI source repository from
https://github.com/clerk/cli.gitif a local source is not provided. This is a vendor-owned repository used as the primary reference for the audit task.\n- [COMMAND_EXECUTION]: Shell commands includingmkdir,cd, andgit cloneare executed to set up the auditing environment. Additionally, if the--applyflag is used, the skill may run local formatting or validation tools to process the updated documentation files.\n- [PROMPT_INJECTION]: The skill processes external source code, which introduces an indirect prompt injection surface.\n - Ingestion points: The skill reads CLI command source files and referenced library files within the
packages/cli-core/src/directory.\n - Boundary markers: No specific delimiters are defined in the instructions to isolate or distinguish ingested source code content from the agent's instructions.\n
- Capability inventory: The skill has the capability to write to local documentation files and execute shell commands for formatting/validation.\n
- Sanitization: No explicit sanitization or validation of the ingested source code content is performed during the audit process.
Audit Metadata