anysearch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the agent to extract API keys from responses and persist them to disk (and also documents a higher-priority --api_key CLI flag and Authorization: Bearer usage), which forces the LLM to handle secret values verbatim in outputs/commands (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md/doc_spec.md describes that, at runtime, the agent ingests user-provided free text as the query argument (general/vertical search and batch_search) and as the url argument for extract, which the AnySearch CLI then sends to https://api.anysearch.com/mcp for processing.