bug-bounty

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

• Third-party content exposure detected (high risk: 0.90). The skill's recon and learn workflows (e.g., /recon, /hunt, recon-agent, Phase 1/2) explicitly instruct crawling and fetching public third‑party content — using tools like waybackurls, gau, katana, HackerOne GraphQL queries, GitHub dorking and JS bundle scraping — and then ingesting/analysing that content to drive hunting, chaining, and tool actions, which meets the criteria for untrusted user-generated web content that can influence the agent's behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill contains explicit install/loader commands that fetch remote skill definitions which will be loaded into the agent and thus can directly control prompts/instructions — e.g. git clone https://github.com/0x1Jar/BountyForge.git and curl -s https://raw.githubusercontent.com/shuvonsec/claude-bug-bounty/main/SKILL.md -o ~/.claude/skills/bug-bounty/SKILL.md (these URLs fetch external SKILL.md content that the agent will load at runtime).