agent-collab-updater

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses an external, public manifest at https://raw.githubusercontent.com/dev-goraebap/agent-collab/main/manifest.json (Step 1 in SKILL.md) and uses its contents to decide updates/renames/removals and to drive CLI actions, so untrusted third-party content can directly influence tool use and behavior.