pingone-to-descope

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a blocking multi-part process (MCP Check, Migration Plan, Execution) that requires explicit user confirmation and review before any code modifications occur.
  • [SAFE]: Credential management follows industry best practices by instructing the user to store temporary read-only tokens in local .env files. The skill explicitly forbids the agent from printing secrets or persisting them in migration documentation.
  • [SAFE]: External network operations and package references target well-known services (Ping Identity) or trusted vendor-owned resources (Descope's official documentation and GitHub repositories).
  • [SAFE]: The skill includes a 'CIAM Scope Guard' to prevent accidental application of migration logic to out-of-scope workforce or employee identity environments, reducing the risk of unintended privilege escalation or configuration errors.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the user's codebase via search tools (grep, rg) to identify migration touchpoints. While this processes untrusted data, the risk is mitigated by the 'Engineer Review Checkpoint' and the fact that generated plans must be reviewed by a human before execution. (Internal Severity: LOW)
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 04:45 PM
Security Audit — agent-trust-hub — pingone-to-descope