Skip to content
SkillModel-led396 tokens in use

competition-prompt-injection

A CTF sandbox workflow for analysing prompt injection, retrieval poisoning and tool-boundary issues in agent challenges.

44,996 stars on the repository MIT Licensezhaoxuya520/reverse-skill · CTF-Sandbox-Orchestrator/competition-prompt-injection
git clone https://github.com/zhaoxuya520/reverse-skill.git
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing competition-prompt-injection costs

107tokens idle
396tokens in use
593tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples0/15
  • Output7/15
  • Size15/15
  • Resources7/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance72
  • Community72
  • Maturity28
  • Momentum40

This skill is a downstream specialization of the ctf-sandbox-orchestrator skill. It covers challenges about trust boundaries inside an agentic system: prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption and secret exposure.

The agent maps the layers (system, developer, user, retrieved, memory, planner, tool response), then documents one minimal chain from untrusted text to a changed tool call or exposed secret, in compact evidence blocks. Replies are in Simplified Chinese unless English is requested.

What You Get

  • A layer map separating system, developer, user, retrieved, memory, planner and tool-response content
  • A minimal proof chain from untrusted content to an observable side effect
  • A reporting rule that names the failing layer: retrieval, summarizer, planner, executor or post-processing
  • Three compact evidence blocks to keep: the source chunk, planner drift and final tool call

Common Use Cases

  • Explaining how a poisoned document changed an agent’s tool arguments in a lab
  • Reviewing memory contamination or planner drift in a sandbox agent chain
  • Writing up a secret exposure caused by an agent tool boundary in a CTF

What Makes It Unique

It treats a malicious string as insufficient proof until a side effect is observed, and it asks the reporter to name which layer failed. It is limited to agent trust boundaries and runs only after the orchestrator skill has set sandbox assumptions.

Under The Hood

The skill is instruction text only: a SKILL.md, one reference checklist and an agent config file that disables implicit invocation. It ships no scripts and does not itself fetch pages, call APIs, run commands or write files. Any observation of the challenge agent uses the tools the user already provides in the sandbox.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers