citation-management

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill prompt instructs the agent to extract an API key directly from a local markdown file via grep/cut and pass it as a command-line argument (--api-key "$(grep ...)"), exposing the secret in the LLM's context and command output.

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

• Third-party content exposure detected (low risk: 0.10). The skill searches Semantic Scholar based on generated queries from LaTeX drafts, which is an active search of external web content rather than ingesting unauthenticated feeds.