outlining

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to call the Zotero MCP with a collection_key taken from .writing/metadata.yaml (collection_key = <metadata.yaml zotero.collection_key>), which requires the LLM/agent to include that secret value verbatim in the tool call/output.

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

• Third-party content exposure detected (high risk: 0.75). At runtime the skill can invoke superpower-writing:literature-review and superpower-writing:research-lookup (Step 2), which typically ingest retrieved web/outsider-authored free text into the agent’s LLM context as it grounds the outline in prior work.