software-devtools

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for building tools and code generators that ingest external, potentially untrusted schemas such as OpenAPI, GraphQL, and Protobuf.
  • Ingestion points: The skill explicitly directs the agent to build workflows around processing external schema files in SKILL.md.
  • Boundary markers: There are no instructions for implementing delimiters or security warnings to prevent agents from obeying instructions embedded within these external data sources.
  • Capability inventory: Not applicable to the skill itself as it contains no code, but the tools described (SDKs, CLIs) are intended to have significant file-system and network capabilities.
  • Sanitization: The skill mentions code formatting and linting for generated output but lacks guidance on sanitizing natural language inputs to prevent injection.
  • [NO_CODE]: The skill is composed entirely of markdown documentation, YAML configuration, and JSON data sources. It does not contain any executable scripts (e.g., shell, Python, JavaScript), which inherently limits its ability to perform unauthorized actions directly.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:03 PM