speakeasy-context

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or exfiltration patterns were identified. The instructions guide the agent in using legitimate vendor tools.
  • [COMMAND_EXECUTION]: The skill utilizes the speakeasy CLI for operational tasks. These commands (agent context, agent feedback) are authenticated components of the Speakeasy development ecosystem provided by the skill author (speakeasy-api).
  • [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for processing external data such as OpenAPI specifications and SDK tasks. While this presents an ingestion surface for untrusted data, the commands utilized are standard tool operations. Evidence: 1. Ingestion points: Speakeasy-related tasks involving SDKs and OpenAPI files (SKILL.md). 2. Boundary markers: Not explicitly defined in this instructional file. 3. Capability inventory: Execution of speakeasy CLI tools (SKILL.md). 4. Sanitization: Relies on the agent's internal safety protocols for processing task-specific data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:45 PM
Security Audit — agent-trust-hub — speakeasy-context