find-software-developer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires the agent to read or obtain a SERVICEGRAPH_TOKEN (from env or .env or via OTP) and explicitly set/use Authorization: Bearer in generated requests and to display/save the token to the user, which forces embedding secret values verbatim in outputs (exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.80). Yes — the SKILL.md requires calling the external ServiceGraph API (https://api.servicegraph.co, e.g., GET /v1/search and GET /v1/get) to ingest firm profiles, URLs, descriptions and contact info from a public third‑party catalog which the agent reads and uses to shortlist and drive outreach/next actions, so untrusted third‑party content can influence behavior.