find-service-providers

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to read or obtain a bearer token (from env/.env or via an OTP exchange) and explicitly to "use" and show/save that token (and set Authorization: Bearer on requests), which requires handling and outputting the secret value verbatim — a direct exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill programmatically fetches and ingests external firm data and third-party listing/rating content from api.servicegraph.co (notably via required /v1/search and /v1/get calls described in SKILL.md), and the agent is instructed to read and act on those briefs/full bundles to shortlist and drive follow-up actions, so untrusted public third‑party content can materially influence decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill requires calling the ServiceGraph API at runtime (notably GET https://api.servicegraph.co/v1/tags?include_values=1) which returns the canonical filter fields/values that the agent must use to build its query prompts, so remote content directly controls the agent's instructions.