ghost-proxy
Starts and controls the reaper MITM proxy to capture, inspect, search, and replay HTTP/HTTPS traffic between clients and servers. Capabilities include starting/stopping the proxy scoped to specific domains, viewing captured request/response logs, searching traffic by method/path/status/host, and inspecting full raw HTTP entries for security analysis. Use when the user asks to "start the proxy", "capture traffic", "intercept requests", "inspect HTTP traffic", "search captured requests", or "view request/response".
95
96%
Does it follow best practices?
Impact
90%
5.00xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Security
3 findings — 1 critical severity, 2 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Suspicious download URL detected (high risk: 0.80). The localhost and example API URLs are benign/placeholders, but the skill explicitly instructs curl|bash of a raw GitHub install.sh (direct download-and-execute from a third‑party repo of uncertain trust), which is a high‑risk pattern for distributing malware.
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
Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the agent starts a MITM proxy that captures arbitrary HTTP/HTTPS traffic and explicitly instructs inspecting logs and raw entries (e.g., "Viewing Captured Traffic" with `reaper logs` and `reaper get`) and using those captured request/response contents in the "Common Workflows / Validate a Security Finding" flow, so the agent will read untrusted third‑party web content that can influence actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill's prerequisite runs a remote install script via curl -sfL https://raw.githubusercontent.com/ghostsecurity/reaper/main/scripts/install.sh | bash, which fetches and executes code from that URL and is required to install the reaper binary before using the skill.
- Repository
- ghostsecurity/skills
- Commit
3c1875a
- 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.