find-skills

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to provide their SKILLSMP_API_KEY (temporarily or persistently) and shows commands that embed that key verbatim (e.g., Authorization: Bearer $SKILLSMP_KEY / inserting the user-provided key into curl), which requires the LLM to handle/output secret values directly and risks exfiltration.

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 results from public sources—skills.sh (via npx skills find) and the skillsmp.com API (e.g., /api/v1/skills/search and /api/v1/skills/ai-search) as described in SKILL.md, meaning untrusted, user-contributed skill metadata is ingested and used to decide/display/install actions.