security-diff-scan

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires the agent to receive and forward tokens/identifiers (e.g., handoffClaimToken, sessionId, scanId) verbatim in tool calls, which forces the LLM to handle secret/token values in its output.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via user-provided prompt/context for setup (e.g., “user-supplied security focus as userContext” and diffTarget resolution) when the skill resolves arguments directly from the user’s initial prompt, before starting app scan execution.