using-sdlc-engineering

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by instructing the agent to process data from external local configuration files.
  • Ingestion points: The agent is directed to check CLAUDE.md for CMMI maturity level configuration.
  • Boundary markers: The instructions lack specific delimiters or safety guidelines to differentiate configuration data from executable instructions.
  • Capability inventory: The skill is designed to load and delegate tasks to other specialist skills within the axiom-sdlc-engineering skillpack.
  • Sanitization: No validation or sanitization protocols are defined for the data ingested from the configuration file.
  • [NO_CODE]: The skill consists entirely of markdown documentation and routing logic and does not include any accompanying Python scripts, Node.js packages, or shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:44 PM