pp-fec

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes explicit templates that embed API keys/tokens (export FEC_API_KEY_QUERY_AUTH "" and fec-pp-cli auth set-token ) and examples showing a "token" field, meaning an agent following the templates could be required to emit secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests user-supplied free text from the end user into fec-pp-cli recall '<user question>' --agent, then reads/uses the resulting candidates/playbook/notes to drive subsequent CLI actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes explicit runtime install instructions that fetch and execute remote code (go install github.com/mvanhorn/printing-press-library/library/other/fec/cmd/fec-pp-cli@latest and go install github.com/mvanhorn/printing-press-library/library/other/fec/cmd/fec-pp-mcp@latest), so these external module URLs are used at runtime to obtain and run code the skill depends on.