
Pentest Project Blackboard
Keeps penetration-test findings in a project database so an agent can resume work without losing context
- Repository
- AIPentest/CyberStrikeAI
- Stars
- 8,323
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent to record each confirmed finding, attack path, and piece of evidence into a SQLite-backed project blackboard as it works, instead of relying on the chat history. Later, the agent can look up stored facts by key, search them, and file formal vulnerability records, so context survives long sessions and context compression. It is written for the CyberStrikeAI penetration-testing product and expects a project to be bound to the conversation first.
Great for
- Security testers running multi-step penetration tests inside the CyberStrikeAI product
- Red-team leads coordinating several sub-agents who need one shared record of findings
- Teams that want structured, linked evidence per target rather than loose notes
Skip it if
- Anyone without authorization to test the targets: the skill drives active exploitation, lateral credential spraying and proxy switching, which is illegal against systems you do not own or have permission to test
- Users outside CyberStrikeAI who lack the matching database tools: the referenced tools (upsert_project_fact, record_vulnerability) exist only in that product, so the instructions will fail elsewhere
- General coding or writing tasks, since the content is entirely about pentest workflow
Try asking
- “Record the open ports and service version I just confirmed on the primary target as a fact”
- “Log this SQL injection on the login form as a finding with its request, response and linked target”
- “Search the project blackboard for facts about the admin subdomain before I try again”
- “List existing vulnerabilities to check for duplicates before recording a new one”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
pentest-blackboard.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip pentest-blackboard.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip pentest-blackboard.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Only use it on targets you are authorized to test, and keep credentials in the redacted form the file recommends
- Install the referenced companion skills too, otherwise the cited workflows will not resolve
- Let the agent call get_project_fact for full details rather than trusting the short index summaries
What's inside
- SKILL.md
Redistributed unmodified from AIPentest/CyberStrikeAI under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.