add-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to "copy the source file content verbatim" when given a file path, so any secrets in that file would be reproduced verbatim in the agent's output (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via $ARGUMENTS (user-provided description or file content) in Phase 1, then writes it into SKILL.md and embeds it into multiple repo files during Phase 4–6.