hunt-source-leak
Hunt source code and build artifact leakage — JavaScript source maps (.js.map) reconstructing TypeScript/ES6 source, Swagger/OpenAPI JSON endpoint discovery, .env/.git exposure, webpack chunks with hardcoded secrets, robots.txt/security.txt recon, build-info files, asset-manifest.json API route discovery, .DS_Store file listing. Use at the START of every recon session — these findings often unlock the entire attack surface.
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
E004: Prompt injection detected in skill instructions.
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
This skill contains explicit, actionable instructions and tooling to discover, retrieve, reconstruct, and extract secrets and source code artifacts (e.g., .env, .git, source maps, Swagger) enabling secret exfiltration and exploitation.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
The document contains explicit, actionable runtime commands and tooling (curl /.env and other paths, download and parse .js.map to extract sources, git-dumper to clone exposed .git, trufflehog/greps to find credentials) intended to retrieve and exfiltrate secrets and gain unauthorized access to targets, demonstrating an intent and viable mechanism to violate users' control over their systems and data.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill's scripts explicitly fetch and display files (head, grep, git grep, base64 decode, etc.) and its guidance to "use key directly" and to look for APP_KEY/DB_PASSWORD/API_KEY means an agent following it would need to read and output discovered secret values verbatim.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The required workflow for “hunt-source-leak” instructs fetching and ingesting outsider-controlled web content from a target (via `curl` to paths like `/.env`, `/swagger.json`, `/static/js/*.map`, and then downloading the `.map` text for reconstruction and secret-grepping), meaning arbitrary external free text from the target is directly read by the LLM at runtime.
- Repository
elementalsouls/Claude-BugHunter
- Revision
7d10e74
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.