github-ops

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

• Third-party content exposure detected (high risk: 0.90). This skill directly calls the public GitHub REST API (see index.js githubApi and functions such as getFileContent, getRepoContents, listIssues, listComments, getPullRequest) and the SKILL.md documents those API flows, so it ingests untrusted, user-generated content from public GitHub repositories/issues/PRs that the agent would read and could materially influence subsequent tool actions (e.g., creating/updating files, triggering workflows).