skillsmp-skill-factory

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt’s examples and APIs require supplying an api_key parameter directly (e.g., factory = SkillFactory(api_key="your-key") and SkillsMPClient(api_key)), which encourages embedding real API keys/credentials into generated code or outputs verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). In “learn”/“orchestrate” modes the runtime calls SkillsMP API endpoints like search_skills() and get_skill_details() to fetch full skill details and search results from an external SkillsMP registry; those returned skill descriptions/specs are free-form text authored by other parties and can be ingested into the agent’s LLM context during analysis/orchestration.