agent-incident

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs embedding API keys directly in CLI arguments (e.g., --api-key ) and in environment variable assignments, which requires the agent to handle or output secret values verbatim and is therefore high-risk.

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

• Third-party content exposure detected (high risk: 0.70). The required workflow uses incident.io API “get/list” commands (e.g., incident get, alert list, oncall schedule entries) whose returned incident/alert/timeline/custom-field text is then ingested into the agent’s LLM context, and that content is outsider-authored (incident.io data created by other users/tenants), creating an indirect prompt-injection risk.