pp-v0

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs replaying playbook steps with slots_resolved substitutions and the recall payload includes a "token" "" and also discusses V0_API_KEY/Authorization: Bearer, which requires the agent to substitute or emit secret API tokens verbatim into commands/requests.

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow ingestion centers on user-provided prompts/questions passed into v0-pp-cli ... --agent and then used for recall/teach, not on outsider-authored third-party free text fetched from an external queue/feed or listing.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes install-time commands that fetch and execute remote code (go install github.com/mvanhorn/printing-press-library/library/ai/v0/cmd/v0-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/ai/v0/cmd/v0-pp-mcp@latest), which are runtime external dependencies that execute remote code.