solve-challenge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly tells the agent to ask the user for a CTFd API token and then set/use it (e.g., export CTF_TOKEN="ctfd_..."), which requires the LLM to accept and potentially embed the secret verbatim in commands or code, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and inspect external URLs and CTF platform pages (e.g., Step 0 CTFd detection with curl and Step 1 "Fetch links") and to use that untrusted public content to guide categorization and invoke follow-up skills, so third-party content can materially influence actions.