Skills
Navigate
skills/celigo/ai/managing-end-users/Gen Agent Trust Hub

managing-end-users

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to process and apply configuration data from external files, which creates a vulnerability to instructions embedded in that data.\n
  • Ingestion points: The agent is instructed to read configuration data from group.json, role.json, and server.json files in references/cli.md, and to use a body parameter for the upsert_mcp_server tool in references/mcp.md.\n
  • Boundary markers: The skill lacks instructions for the agent to use delimiters or ignore potential commands hidden within the JSON structures of these files.\n
  • Capability inventory: The skill uses the celigo CLI to execute administrative commands and the upsert_mcp_server tool to update server settings, providing significant leverage if an injection occurs.\n
  • Sanitization: No validation or sanitization steps are defined for the content of the configuration files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 05:34 AM