testing-api-tester
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and associated execution script (run.sh) follow standard and safe patterns for AI agent skills. No evidence of malicious prompt injection, data exfiltration, or unauthorized command execution was found.
- [PROMPT_INJECTION]: A potential surface for indirect prompt injection exists because the skill is designed to process untrusted external data in the form of API specifications and documentation. 1. Ingestion points: API specifications, documentation, and contract requirements (SKILL.md). 2. Boundary markers: None are explicitly defined in the instructions to separate external documentation from agent instructions. 3. Capability inventory: The skill is intended to generate and facilitate the execution of automated test suites (SKILL.md). 4. Sanitization: No specific sanitization or validation logic for external documentation content is mentioned. This represents a standard vulnerability surface for skills processing external documentation.
Audit Metadata