reporting-sensitive-encrypted-gh-issues

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

• Third-party content exposure detected (high risk: 0.85). The skill is gh-issue-decrypt, which at runtime scans and decrypts GitHub issues/comments from a specified OWNER/REPO via the GitHub API/CLI; those issue body texts are outsider-authored free-form content that the tool reads and then feeds into its LLM context for processing.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs users to run a runtime installation command that fetches and pipes remote code to bash from https://raw.githubusercontent.com/Dicklesworthstone/misc_coding_agent_tips_and_scripts/main/gh-issue-decrypt?$(date +%s), which executes remote code as a required install step.