sota-api-design

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit external API specifications and source code provided by the user, creating a surface for indirect prompt injection.
  • Ingestion points: The agent is directed to read and evaluate API specifications (OpenAPI, GraphQL SDL, Protobuf) and source code files (Java, Python, Go, etc.) as part of its 'AUDIT mode' described in SKILL.md and the Audit checklist sections of all rules files.
  • Boundary markers: The instructions do not provide specific delimiters or 'ignore embedded instructions' warnings for the agent to use when processing audited content.
  • Capability inventory: To perform audits, the agent uses file reading capabilities and shell commands (e.g., grep, printf) to scan local codebases for patterns, as seen in the checklists throughout the rules directory.
  • Sanitization: There are no requirements for sanitizing or filtering the content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 10:22 AM