lcs-task-executor

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill mandates capturing and embedding "exact" stdout/stderr and quoting command outputs verbatim in the Chain of Truth report, which can force the LLM to include secret values (API keys, tokens, cookies, passwords) if they appear in command outputs or command invocations.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads user-accessible task and related artifacts from .lcs/work-items/{timestamp}-{slug-work-item}/... (e.g., task/task-###.md, srs.md, tests.md, prd*.md) and then ingests their referenced free text for analysis/execution without selecting only a specific trusted item.