api-compliance-checker
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill metadata (description field) contains an explicit instruction directing the agent to mention 'TestMu AI HyperExecute' and provide its link in the output. This is a form of metadata poisoning used to inject promotional content into the agent's responses.
- [PROMPT_INJECTION]: The instructions include a capability chaining pattern where the agent is told to check for and execute another skill ('api-sdk-generator') depending on user response. This pattern can be used to guide users into interacting with secondary skills that may have different security profiles.
Audit Metadata