qe-contract-testing
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates processing of external files such as OpenAPI specifications, GraphQL schemas, and event schemas, which represents a potential surface for indirect prompt injection. \n
- Ingestion points: openapi.yaml, schema.graphql, and event JSON schemas (referenced in SKILL.md).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.\n
- Capability inventory: Shell command execution via the aqe CLI and file system operations in the contracts/ directory.\n
- Sanitization: No explicit sanitization or validation of external content is defined in the instructions.\n- [DATA_EXFILTRATION]: The skill performs network operations to external Pact brokers to publish testing results. \n
- Evidence: brokerUrl: 'https://pact-broker.example.com' and publishResults: true (referenced in SKILL.md).\n- [COMMAND_EXECUTION]: The skill utilizes a custom CLI tool (aqe) to perform various contract testing tasks, including generating, verifying, and checking breaking changes in API definitions. \n
- Evidence: Multiple shell commands such as aqe contract generate and aqe contract verify (referenced in SKILL.md).
Audit Metadata