google-serper-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt explicitly instructs running printenv SERPER_API_KEY, which would expose the raw API key value to the agent/LLM (an unnecessary print of a secret), even though the script itself uses env vars safely.

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts/serper_search.py call google.serper.dev search endpoints to retrieve web/news/image search results (organic snippets, links, knowledgeGraph) and SKILL.md requires the agent to read and summarize those results, which are untrusted public web content that could carry indirect prompt-injection risks.