mcaf-feature-spec

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Attack Surface.
  • Ingestion points: The skill identifies docs/Architecture.md and the nearest AGENTS.md as primary inputs for defining feature behavior.
  • Boundary markers: The instructions do not specify the use of delimiters or protective headers to isolate content ingested from the repository from the agent's core instructions.
  • Capability inventory: The skill possesses file-write capabilities for documentation, code, configuration, and CI artifacts, and it defines a workflow for the agent to execute build and test commands based on the generated specifications.
  • Sanitization: There is no mention of sanitizing or validating the contents of source documentation before it is interpolated into the agent's output generation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:18 AM