alterlab-protocolsio

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs embedding a Bearer access token in Authorization headers and provides code examples with a token variable (e.g., "YOUR_ACCESS_TOKEN"), which implies the agent would need to insert real secret tokens verbatim into generated requests or code, creating exfiltration risk.

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 ingests public, user-generated content from protocols.io (e.g., GET /protocols, GET /publications, GET /protocols/{id}/comments) as shown in SKILL.md workflows like "Workflow 1: Import and Analyze Protocol" and in references/discussions.md, and instructs the agent to read and act on that content (extract/parse steps, review comments, update or publish protocols), which exposes it to untrusted third-party instructions.