breaking-change-detector

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection because it processes untrusted API specifications as input for its analysis logic.
  • Ingestion points: Processes user-provided Version A and Version B specifications for diff analysis in the SKILL.md protocol.
  • Boundary markers: No delimiters or instructions are specified to isolate the content of the API specifications from the agent's core instructions.
  • Capability inventory: The skill specifies the capability to write markdown and JSON reports to the docs/api-report/ directory.
  • Sanitization: No specific sanitization, validation, or escaping of the input specification content is defined before the analysis or report generation.
  • [NO_CODE]: The skill does not contain any executable scripts, binary files, or external dependencies, operating entirely through instructions and configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:19 AM