pp-discogs

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows a live "token" value in playbook slots_resolved and instructs agents to substitute slots_resolved into playbook steps, which would require the LLM/agent to include secret token values verbatim in generated commands/outputs.

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

• Third-party content exposure detected (medium risk: 0.30). Source: the required workflow’s agent-mode “recall” step runs discogs-pp-cli recall "<user's question>" --agent, so outsider-authored free text from the user question is ingested at runtime to drive command/teach logic.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing remote code at runtime (e.g., via "npx -y @mvanhorn/printing-press-library install discogs --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/discogs/cmd/discogs-pp-cli@latest" / "go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/discogs/cmd/discogs-pp-mcp@latest"), which fetches and executes remote code and is a required dependency for the skill.