Not in the top 1,000 by GitHub stars
Alpha-Park/genpark-agent-redteam-indirect-injection-fuzzer-skill
Agentic cybersecurity red-teaming indirect prompt injection fuzzer with delimiter evasion, unicode homoglyph generation, and threat entropy scoring.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → edce1b0954aa
No earlier version was observed for comparison.
0GitHub stars
Not availablestars in 7 days
1skill in this repository
10commits in 30 days
Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
genpark-agent-redteam-indirect-injection-fuzzer-skill
When your agent uses it
Agentic cybersecurity red-teaming indirect prompt injection fuzzer with delimiter evasion, unicode homoglyph generation, and threat entropy scoring.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
485 tokensWhen the skill is activated
Reference documents
410 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview & Agent Behavioral Directives
- When to Activate This Skill
- How to Execute
- Core Mathematical & Algorithmic Guardrails
Scripts executed separately
client.pyexample_usage.pymcp_server.py
Files
.gitignoreasset57 bytesLICENSEasset1,071 bytesREADME.mddoc1,663 bytesSKILL.mdcore2,250 bytesSKILL.mdcore2,250 bytesclient.pyruns3,979 bytesexample_usage.pyruns1,188 bytesmcp_server.pyruns1,646 bytesrequirements.txtdoc75 bytesskill.jsonasset552 bytes
Read SKILL.md
# Genpark Agent Redteam Indirect Injection Fuzzer Skill
## Overview & Agent Behavioral Directives
You are an autonomous agent specialized in **Genpark Agent Redteam Indirect Injection Fuzzer Skill**.
Your primary directive is to execute: Agentic cybersecurity red-teaming indirect prompt injection fuzzer with delimiter evasion, unicode homoglyph generation, and threat entropy scoring.
Always ensure mathematical precision, parameter validation, and deterministic outputs.
## When to Activate This Skill
- Activate when an agent workflow or user instruction requires:
- `{'name': 'generate_fuzz_variants', 'description': 'Generate adversarial prompt injection test cases.'}`
- `{'name': 'audit_prompt_for_injection', 'description': 'Scan untrusted inputs and RAG contexts for prompt injection threats.'}`
- Activate when operating in zero-dependency environments requiring pure Python standard library execution.
## How to ExecuteSkills included
- genpark-agent-redteam-indirect-injection-fuzzer-skill
Repository facts
- License
- MIT
- Created
- Oct 29, 2026
- Last pushed
- Oct 31, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 6 network referencesin 1 file: README.md:3
- No hidden or obfuscated text
- 4 instruction override signalsin 3 files: client.py:19 example_usage.py:20 mcp_server.py:20
- 3 executable scriptsin 3 files: client.py:1 example_usage.py:1 mcp_server.py:1
- 1 reference to secretsin 1 file: .gitignore:3
- No requests to vote in Hot
Show all 14 signals by file
.gitignore
- Access to secretsline 3
[Credential-related source omitted]
README.md
- Network accessline 3
[](https://github.com/alphaparkinc) - Network accessline 4
[](https://modelcontextprotocol.io) - Network accessline 5
[](#) - Network accessline 6
[](#) - Network accessline 7
[](#) - Network accessline 8
[](LICENSE)
client.py
example_usage.py
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 13 facts
- Network access in prose of documentationREADME.md:3Low confidence
- Network access in prose of documentationREADME.md:4Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:8Low confidence
- Executable script in a comment of a file that runsclient.py:1Low confidence
- Instruction override signal in code of a file that runsclient.py:19Low confidence
- Instruction override signal in code of a file that runsclient.py:20Low confidence
- Executable script in a comment of a file that runsexample_usage.py:1Low confidence
- Instruction override signal in code of a file that runsexample_usage.py:20Low confidence
- Executable script in a comment of a file that runsmcp_server.py:1Low confidence
- Instruction override signal in code of a file that runsmcp_server.py:20Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
