dev-loop-api-client-generator
Warn
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill implementation includes Python patterns and shell command examples for executing external code generation utilities. Specifically, the OpenAPIClientGenerator class in SKILL.md uses subprocess.run to invoke tools like npx and openapi-generator-cli.
- [EXTERNAL_DOWNLOADS]: The skill references and encourages the use of various third-party tools and packages from well-known registries, including @openapitools/openapi-generator-cli, Microsoft's kiota, and numerous language-specific HTTP and testing libraries.
- [METADATA_POISONING]: Ten separate reference files (e.g., references/architecture-patterns.md, references/performance-optimization.md, references/security-best-practices.md) contain 150 repetitive sections of technical filler text. These files are misleadingly presented as advanced technical specifications for senior engineers, but the redundant content serves only to bloat the context window and can degrade the reasoning performance of AI agents.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves processing API specifications from potentially untrusted external sources.
- Ingestion points: The inputSpec configuration field and the Python spec_path attribute (file: SKILL.md).
- Boundary markers: Absent. The instructions do not provide delimiters or warnings for the agent to ignore instructions embedded within the specifications.
- Capability inventory: The skill possesses capabilities for shell command execution and Python subprocess management (file: SKILL.md).
- Sanitization: Absent. There is no evidence of validation or filtering applied to the specification content prior to its use in code generation workflows.
Audit Metadata