PE
pentest-redteam-ops
Coordinate autonomous pentest skills with dependency enforcement, deconfliction, and emergency stop controls.
Install
mkdir -p .claude/skills/pentest-redteam-ops && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17039" && unzip -o skill.zip -d .claude/skills/pentest-redteam-ops && rm skill.zipInstalls to .claude/skills/pentest-redteam-ops
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Coordinate autonomous pentest skills with dependency enforcement, deconfliction, and emergency stop controls.109 charsno explicit “when” trigger
About this skill
Pentest Red Team Ops
Stage
- PTES: all
- MITRE: Full ATT&CK chain
Objective
Run full engagement sequencing and produce timeline and status dashboards.
Required Workflow
- Validate scope before any active action and reject out-of-scope targets.
- Run only authorized checks aligned to PTES, OWASP WSTG, NIST SP 800-115, and MITRE ATT&CK.
- Write findings in canonical finding_schema format with reproducible PoC notes.
- Honor dry-run mode and require explicit --i-have-authorization for live execution.
- Export deterministic artifacts for downstream skill consumption.
Execution
python skills/pentest-redteam-ops/scripts/redteam_ops.py --scope scope.json --target <target> --input <path> --output <path> --format json --dry-run
Outputs
engagement-log.jsonredteam-timeline.jsonorchestration-report.json
References
references/tools.mdskills/autonomous-pentester/shared/scope_schema.jsonskills/autonomous-pentester/shared/finding_schema.json
Legal and Ethical Notice
WARNING AUTHORIZED USE ONLY
This skill executes real security testing tools against live targets.
Use only with written authorization.