iac-security

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to detect and report hardcoded secrets and include "Evidence: " from IaC and state files, which requires extracting and outputting literal secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow ingests the contents of IaC files discovered via glob patterns (e.g., **/*.tf, cloudformation/**/*.yaml, **/*.bicep) and then feeds those file contents into the LLM for analysis; since these files may be authored by outsiders (e.g., repo contributors), this is an outsider-authored free-text injection surface.