aidlc

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill mandates logging "ALL user inputs" into aidlc-docs/audit.md and loading/saving workspace artifacts, which forces the agent to record or reproduce any user-provided secrets or credentials verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's installer (install.sh) clones the public GitHub repo https://github.com/awslabs/aidlc-workflows.git and SKILL.md then explicitly requires the agent to read and follow files under .claude/skills/aidlc/aidlc-workflows/... (e.g., core-workflow.md), meaning the agent will ingest and act on open/public third‑party content that can alter its behavior.