Skip to content

feat(cicd): add offensive-claude-code-action #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sushant-me wants to merge 1 commit into
base: main
Choose a base branch
from
+416 −4
Open

feat(cicd): add offensive-claude-code-action #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@ All notable changes to `claude-red` are documented here. The library follows a p

## [Unreleased]

### Added

- **cicd/** — `offensive-claude-code-action`: offensively assessing AI coding agents wired into CI (`anthropics/claude-code-action` and the Codex/Gemini/Copilot equivalents). Prompt injection from issue, PR and comment text into an agent holding a write token; context-file injection via `CLAUDE.md`/`AGENTS.md` loaded from the PR head; tool-allowlist abuse for `Bash`/`Write`/`WebFetch`; `pull_request_target` with an untrusted checkout; exfiltration through the agent's own reply, commits and PRs; repository persistence by rewriting workflows; OIDC trust-policy abuse; MCP tool poisoning; and denial-of-wallet. Includes recon commands, per-surface payload shapes, an execution-marker technique for reproducible proof, a defender view, and a hardening checklist to verify.

### Changed

- Replaced an inactive EXIF viewer reference in `offensive-osint` with a browser-local metadata viewer and added evidence-corroboration guidance.
Expand Down
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ Paste the contents of a `SKILL.md` into a Project's system prompt or prepend it
| [Reconnaissance](#reconnaissance) | 2 | OSINT tooling and structured intelligence collection |
| [API Security](#api-security) | 2 | REST/gRPC/WebSocket testing, business logic abuse |
| [Container & Kubernetes](#container--kubernetes) | 2 | Container escape, Kubernetes cluster exploitation |
| [CI/CD & Pipeline](#cicd--pipeline) | 2 | Pipeline exploitation, secrets extraction |
| [CI/CD & Pipeline](#cicd--pipeline) | 3 | Pipeline exploitation, agent-in-CI abuse, secrets extraction |
| [Cryptography](#cryptography) | 2 | Cryptographic implementation attacks, TLS/SSL |
| [Privilege Escalation](#privilege-escalation) | 2 | Linux and Windows privilege escalation |
| [Post-Exploitation](#post-exploitation) | 3 | Lateral movement, persistence mechanisms, data exfiltration |
Expand Down Expand Up @@ -259,6 +259,7 @@ Paste the contents of a `SKILL.md` into a Project's system prompt or prepend it
|---|---|
| [`offensive-cicd-pipeline`](Skills/cicd/offensive-cicd-pipeline/SKILL.md) | CI/CD exploitation — GitHub Actions injection, Jenkins RCE, GitLab CI abuse |
| [`offensive-cicd-secrets`](Skills/cicd/offensive-cicd-secrets/SKILL.md) | CI/CD secrets — environment variable extraction, vault misconfigs, runner token abuse |
| [`offensive-claude-code-action`](Skills/cicd/offensive-claude-code-action/SKILL.md) | AI coding agents in CI — prompt injection from issue/PR text into an agent holding a write token, tool-allowlist abuse, exfiltration |

### Cryptography

Expand Down
Loading