Automated summary
Exposes the pwn_eval Ruby module PWN::AI::Context to ingest local evidence (files, disassembly, hexdumps, HTTP transcripts) and later retrieve it.
Strengths
- Single documented entry point for evidence ingestion in pwn_eval, so nothing needs to be reimplemented in shell
- Purpose-built attach methods already cover disassembly, files, hexdumps and HTTP transcripts
- Explicit policy: unavailable embeddings are never replaced by synthetic vectors
- Straightforward integration check with respond_to?(:authors) once the module is loaded
Limitations
- Documentation is generated and thin: parameter names must be read from pwn/ai/context_ingestion.rb
- Assumes a Ruby environment with pwn_eval and the allowed tools (pwn, pwn_eval) already available
- retrieve quality depends entirely on locally ingested evidence, with no external embedding fallback
Use it when a pwn_eval task requires collecting and querying local evidence such as binaries, hexdumps or HTTP traces through PWN::AI::Context.
Avoid it outside the pwn_eval ecosystem, or if you expected semantic search backed by remote embeddings.
Security analysis
CautionThe skill documents a local evidence ingestion module and explicitly says not to reimplement in shell. It does not instruct destructive, exfiltrating, or obfuscated actions. However, because pwn_eval can execute code and file-related methods exist, caution is warranted.
- •Uses pwn_eval, a potentially powerful code execution tool, though the skill restricts usage to specific PWN::AI::Context class methods.
- •Methods like attach_file and ingest may read local files, but no exfiltration or destructive actions are instructed.
Examples
Use PWN::AI::Context to ingest this binary along with its disassembly, then retrieve the context around the main parsing routine.Attach this HTTP transcript to PWN::AI::Context and retrieve the evidence related to the authentication endpoint.Run PWN::AI::Context.help and list the public methods available before calling ingest.name: pwn-ai-context description: Drive PWN::AI::Context from pwn_eval. license: MIT allowed-tools: [pwn, pwn_eval] metadata: bundled: true generated: true module: PWN::AI::Context source: pwn/ai/context_ingestion.rb
PWN::AI::Context
Local evidence ingestion; unavailable embeddings never become synthetic vectors.
When to use
Call PWN::AI::Context from pwn_eval when the task needs this module.
Do not reimplement it in shell.
Methodologies
Generated from pwn/ai/context_ingestion.rb. Prefer the public class methods below.
Class methods take (opts = {}) and read opts.
How to call
PWN::AI::Context.help
PWN::AI::Context.ingest(opts)
Public methods
authorsingestretrievehelpattach_disasmattach_fileattach_hexdumpattach_http_transcript
References
references/urls.md— URLs from source
Source
pwn/ai/context_ingestion.rb
Verification
PWN::AI::Context.respond_to?(:authors) after the
module is loaded. Read the source for parameter names.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/pwn-ai-context-context-ingestion-mtwgrt3o/download' --output '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md.part' && mv '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md.part' '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md' && test -s '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/pwn-ai-context' && cp -R '.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o' '.claude/skills/pwn-ai-context'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o'openskills read 'pwn-ai-context-context-ingestion-mtwgrt3o'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/pwn-ai-context-context-ingestion-mtwgrt3o/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
DeFi AMM Security
Security
Security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, donation attacks, oracle manipulation, slippage, and integer math.
Semgrep Rule Creator
Security
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Includes test-first methodology, taint mode support, and validation steps. Helps when building targeted static analysis detections.
Dev Toolbar Review Guide
Security
Safety rules for the dev toolbar, PostHog client, and feature flags. Use when reviewing changes to dev-tools and related files, covering environment guards, override cookies, and SSE stream safety.