swagger-doc-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): This skill is vulnerable to indirect prompt injection because it processes untrusted API documentation files. Evidence: 1. Ingestion points: Reads Swagger/OpenAPI specs from the workspace. 2. Boundary markers: Absent. 3. Capability inventory: Uses Bash, curl, Read, and Write tools. 4. Sanitization: Absent.\n- Command Execution (LOW): The skill requests the Bash tool with a wildcard curl permission (curl:*). While no malicious commands are present in the skill itself, this provides a broad capability that could be exploited by malicious input data processed by the agent.\n- No Code (SAFE): The skill contains no executable scripts or complex logic, consisting only of descriptive markdown and metadata tool requests.
Audit Metadata