pp-algolia

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's playbook/recall protocol includes a "slots_resolved" entry with a "token" and explicitly instructs replaying steps with slots_resolved substitution, which forces the agent to insert live token/API-key values verbatim into generated commands—an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow takes outsider-authored user text as the “user's question” input to algolia-pp-cli recall "<user's question>" --agent, which then reads and follows surfaced playbook.notes / candidates[].next_action verbatim to drive further actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill includes installation commands that fetch and build remote Go modules used at runtime (e.g., "go install github.com/mvanhorn/printing-press-library/library/developer-tools/algolia/cmd/algolia-pp-mcp@latest"), which would download and execute remote code as a required dependency.