find-management-consultant

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to read bearer tokens from environment or .env files, run an OTP flow that returns a bearer token, set Authorization: Bearer on requests, and explicitly tells the user to "save this" (i.e., show the token), which requires handling and often outputting secret token values verbatim.

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly queries the external ServiceGraph API and ingests third-party firm data (notably GET /v1/get which returns url, phone, email, social, legal_name, address and firm text/bio) and the agent is required to read and use that content to shortlist/enrich and drive next actions, so untrusted public content could indirectly inject instructions.