octocode-rfc-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research phase explicitly instructs the agent to run "Track B — External best practices (GitHub + npm + web)" using tools like githubSearchCode, packageSearch, and WebFetch to ingest public GitHub repos, npm pages, docs, and blog URLs, and those external findings are required evidence that will influence RFC recommendations and next actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs using githubGetFileContent / WebFetch to fetch external files (e.g., https://github.com/rust-lang/rfcs/blob/master/0000-template.md and raw.githubusercontent.com-hosted files) at runtime and inject those contents into the agent's research/context, which means remote URLs can directly control prompts/instructions used by the agent.