clerk-orgs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of untrusted project data (source code, database schemas, README files) to determine if a project should use Clerk Organizations, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The skill instructions in
SKILL.mddirect the agent to analyze project files, search for specific database foreign keys (e.g.,workspace_id,team_id), and evaluate UI copy for terms like "Invite your team" or "Admin". - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the analyzed project content.
- Capability inventory: The skill possesses significant capabilities including the ability to perform network requests via
WebFetchand execute organization management tasks via theclerkCLI (e.g., creating/deleting organizations, managing memberships, sending invitations). - Sanitization: There is no evidence of sanitization or validation performed on the ingested project data before it is processed by the agent.
Audit Metadata