skills/openclaw/skills/openapi2cli/Gen Agent Trust Hub

openapi2cli

Warn

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill uses uvx to download and execute openapi2cli from PyPI. While PyPI is a standard registry, the author (Olafs-World) is not a recognized trusted source, and the tool's behavior involves generating executable code from remote inputs.
  • [DYNAMIC_EXECUTION] (MEDIUM): The primary function is to generate a Python script from an OpenAPI spec and subsequently execute it. This 'Script generation + execution' pattern is risky because if the input specification (JSON/YAML) is compromised or malicious, it could lead to the generation and execution of arbitrary code.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests untrusted data from remote URLs to drive the CLI generation process.
  • Ingestion points: OpenAPI spec URLs passed to openapi2cli generate.
  • Boundary markers: None specified; the tool appears to process the entire remote file into code structure.
  • Capability inventory: File system writing (creating the CLI script) and subprocess execution (running the generated script).
  • Sanitization: No evidence of sanitization or validation of the OpenAPI spec's logic to prevent malicious code generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 09:36 PM