bugbounty-ideas

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

• Third-party content exposure detected (low risk: 0.10). Workflow step 3/31–32 can search online and fetch selected external links (including potentially attacker-chosen URLs), so the runtime may ingest outsider-authored free text from those fetched pages.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to fetch links from the bundled README at runtime (e.g., https://github.com/devanshbatham/Awesome-Bugbounty-Writeups#cross-site-scripting-xss), and those external writeups would be injected into the agent's context and therefore directly influence prompts/output.