ticket-triage

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to read/fetch ticket content (including files or pasted text) and to "quote the problematic text from the ticket directly," which would force the LLM to reproduce any embedded secrets (API keys, tokens, passwords) verbatim in its output.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly says it may "fetch[] an issue from Jira/Linear/GitHub / other tracker" as part of "How to Get the Ticket," which means it will ingest user-generated, potentially public third‑party issue content and act on it as part of its triage workflow, exposing the agent to indirect prompt injection risk.