security-scanner

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly scans config files like .env and requires including "the actual vulnerable code snippet as evidence" and flagging hardcoded secrets, which forces the agent to read and potentially output secret values verbatim in its report.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md instructs Step 1 to ask the user for an arbitrary GitHub repository URL and then clone it (“gh repo clone …”), after which the scanner reads the cloned project’s source/config files into the report via Step 2/3; those are outsider-authored files provided by a non-selected party.