configure-integration-oauth
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers shell commands using
pnpm exec vitestandpnpm test:integration. These operations are used to run local test suites such aspackages/integration-auth/src/oauth.test.tsandapps/control-plane/src/auth/hosted-oauth-broker-contract.test.tsto verify integration logic. - [INDIRECT_PROMPT_INJECTION]: The skill has a potential vulnerability surface for indirect prompt injection as it instructs the agent to ingest and act upon data from external files within the project, including
docs/integration-oauth.mdand provider definitions inpackages/integration-catalog. - Ingestion points:
docs/integration-oauth.md,packages/integration-catalog, andapps/control-plane/.env.example. - Boundary markers: None specified in the instructions to separate documentation content from agent instructions.
- Capability inventory: The skill possesses shell command execution capabilities via
pnpm. - Sanitization: No sanitization or validation of the documentation content is mentioned before the agent processes the instructions.
Audit Metadata