validating-api-schemas

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and example code use npx to download and execute validation utilities from the npm registry (e.g., @stoplight/spectral-cli, oasdiff, ajv-cli). These are well-known tools from a reputable package registry, used here for their intended purpose.\n- [COMMAND_EXECUTION]: The skill executes shell scripts and CLI tools for structural validation and linting of API specifications. These commands operate on local files identified by the user or the project structure.\n- [PROMPT_INJECTION]: The skill analyzes external API specification files, which represents a surface for indirect prompt injection. A maliciously crafted schema could contain instructions intended to influence the agent's behavior during the validation process.\n
  • Ingestion points: Specification files located via Glob and Read tools as described in SKILL.md.\n
  • Boundary markers: The instructions do not specify explicit delimiters or warnings to ignore instructions embedded within the schema data.\n
  • Capability inventory: The skill uses Bash, Read, Write, and Edit tools to process schemas and generate reports.\n
  • Sanitization: There is no mention of sanitizing or escaping the content of the schema files before they are processed by the agent or validation scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 04:13 PM