0dayinc/pwn/tool-guard

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Drive PWN::AI::Agent::ToolGuard from pwn_eval.

Install

npx vskill@latest install 0dayinc/pwn/tool-guard

SKILL.md

PWN::AI::Agent::ToolGuard

Shared pre-dispatch guards for the two high-volume runtime tools (shell / pwn_eval). Rejects placeholder payloads, aliases wrong schema keys, and names the shell that will actually run the command.

When to use

Call PWN::AI::Agent::ToolGuard from pwn_eval when the task needs this module. Do not reimplement it in shell.

Methodologies

Generated from pwn/ai/agent/tool_guard.rb. Prefer the public class methods below. Class methods take (opts = {}) and read opts.

How to call

ruby
PWN::AI::Agent::ToolGuard.help
PWN::AI::Agent::ToolGuard.unwrap_payload(opts)

Public methods

  • unwrap_payload
  • present
  • placeholder
  • placeholder_match
  • bashism
  • bashism_match
  • shell_syntax_surface
  • mint_canary
  • canary_leak
  • injection_score
  • quarantine_output
  • shell_bash
  • shell_name
  • protect_http
  • protect_core_constants
  • coerce_args
  • invalid_payload
  • denial
  • host_load
  • deadline_s
  • reset_timeout_budget
  • mutation_count
  • payload_spent
  • note_timeout
  • next_timeout
  • timeout_lesson
  • timeout_result
  • timeout_prior_count
  • refuse_copied_persist
  • scope_refusal
  • policy_decision
  • scope_check
  • rfc1918
  • ip_in_cidr
  • command_class
  • record_runtime
  • predicted_timeout
  • auto_job
  • authors
  • help
  • auto_job?
  • bashism?
  • canary_leak?
  • ip_in_cidr?
  • note_timeout!
  • placeholder?
  • present?
  • protect_core_constants!
  • protect_http!
  • refuse_copied_persist?
  • reset_timeout_budget!
  • rfc1918?
  • scope_check!
  • shell_bash?

Source

pwn/ai/agent/tool_guard.rb

Verification

PWN::AI::Agent::ToolGuard.respond_to?(:unwrap_payload) after the module is loaded. Read the source for parameter names.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
86
Repository forks
12
7-day trend score
27

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/0dayinc/pwn/tool-guard/badge)](https://verified-skill.com/skills/0dayinc/pwn/tool-guard)

Something wrong with this skill or its page? Tell us.