typespec-api-operations

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for interacting with external APIs, which represents a potential vector for indirect prompt injection if the API returns malicious data.
  • Ingestion points: The listItems and getItem operations in SKILL.md define how external data is ingested into the agent context.
  • Boundary markers: The templates do not define explicit boundary markers or instructions to ignore embedded instructions.
  • Capability inventory: The skill defines write-capable operations such as createItem, updateItem, and deleteItem in SKILL.md.
  • Sanitization: No input validation or output sanitization is defined in the TypeSpec schemas.
  • [SAFE]: The skill consists of declarative schema definitions and documentation intended for developers. It does not contain any executable scripts, hardcoded credentials, or unauthorized network activity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:51 AM
Security Audit — agent-trust-hub — typespec-api-operations