apple-app-store-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.85). The skill mostly encourages reading FREVANA_TOKEN from the environment (secure) but explicitly documents and exemplifies a --token override that embeds a bearer token on the command line, which would require the LLM to include secret values verbatim in generated commands (exfiltration risk).

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

• Third-party content exposure detected (low risk: 0.10). The runtime path scripts/search_apple_app_store.sh reads user-supplied --term into the POST payload to https://ai-factory.frevana.com/service/apple-app-store-search, and the LLM-facing result is the returned JSON payload (derived from that query), but there is no outsider-free-text ingestion from an external feed/inbox/issue/ticket without explicit user term selection.