api-integration-specialist
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: The agent processes user-provided descriptions and requirements for API architectures as shown in the examples within
references/agents/api-integration-specialist.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the user-supplied text.
- Capability inventory: The agent is configured with high-privilege tools including
Read,Write,MultiEdit,Bash,Grep, andGlobas specified in the reference file. - Sanitization: There is no evidence of input sanitization or validation performed on the data ingested from user prompts.
Audit Metadata