add-image-vision

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The URL points to an external GitHub repository owned by an unknown account and the skill explicitly instructs adding it as a git remote and merging its branch (including new source files and dependencies), which is a common vector for introducing malicious code or supply‑chain compromises even though the link itself is to GitHub rather than a direct executable.

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

• Third-party content exposure detected (high risk: 0.90). The skill downloads WhatsApp group image attachments and passes them to the agent as base64-encoded multimodal content blocks (see Phase 2 changes to src/* and Phase 4 verification in SKILL.md), so it ingests untrusted, user-generated third-party content that the agent interprets.