openaffiliate

Warn

Audited by Snyk on Nov 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow runs search_programs and get_program against the public OpenAffiliate community registry, which returns program descriptions, restrictions, and agentPrompt text that outsiders can submit, but the agent must actively search and fetch those items and cannot be forced to ingest them.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The skill's MCP server at openaffiliate.dev/mcp is an inbound source whose agentPrompt guidance the agent is told to read and treat as program guidance before recommending, which is behavior-selecting content; the publisher is an open registry with a linked organization-owned GitHub repo but no strong first-party or cryptographic provenance, so it is common/reputable unofficial, giving medium.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 16, 2026, 09:37 PM
Issues
2