konnect-api-publish
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data and utilizes tools with mutation capabilities, creating a surface for indirect prompt injection.
- Ingestion points: The skill ingests data from managed API inventory, version objects, API specifications, and descriptive metadata as noted in SKILL.md.
- Boundary markers: The instructions lack defined boundaries or delimiters to separate untrusted external data from the agent's internal control instructions.
- Capability inventory: The skill is authorized to use mutation tools such as kongctl-declarative, terraform-konnect, and deck-gateway to modify the Konnect platform state.
- Sanitization: No evidence is provided for the sanitization or validation of ingested content (e.g., API specifications) before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill's workflow relies on the execution of specialized command-line tools to interact with the Konnect platform.
- Evidence: SKILL.md details the use of kongctl-query, kongctl-declarative, terraform-konnect, and deck-gateway. These tools are vendor-aligned for the 'kong' author and are intended for the skill's operational purpose.
Audit Metadata