CtrlK
BlogDocsLog inGet started
Tessl Logo

hunt-cicd

Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a dense, executable offensive-security playbook that respects Claude's competence, leads each finding with a proof gate, and supplies concrete commands plus false-positive retractions throughout. Organization is clean and self-contained with no wasted nesting.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no 'what is Jenkins/GitHub Actions' exposition, just recon commands, payloads, and verdicts. Time-sensitive CVE/version details are quarantined in a 'Grounded References' section rather than scattered, so they do not pad the working sections.

3 / 3

Actionability

Every phase ships fully executable, copy-paste-ready commands — curl fingerprinting, the Groovy credential-store dump, the java CLI CVE-2024-23897 exploit, gh/jq workflow enumeration, and trufflehog docker scanning — with placeholders like $TARGET and <COLLAB> clearly marked.

3 / 3

Workflow Clarity

A clear Phase 1–6 sequence is gated by the 'It-Didn't-Happen-Without-Proof' front gate and reinforced by per-finding 'Validation Discipline' checkpoints plus a 'Common false positives to retract' list — explicit validate→retract feedback loops for these high-risk offensive operations.

3 / 3

Progressive Disclosure

No bundle files exist, so the single SKILL.md is appropriately organized into well-signaled sections (Crown Jewel Targets, proof gate, phases, references, chain table, validation discipline) with no deeply nested references, satisfying the simple-skill allowance for a 3.

3 / 3

Total

12

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, third-person statement that names many concrete CI/CD exploitation actions and pairs them with an explicit 'Use when...' trigger clause anchored on observable target conditions. It is distinctive and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete vulnerability classes and actions — 'GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage' — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both 'what' (the enumerated vuln-hunting actions) and 'when' via an explicit 'Use when target has a public GitHub/GitLab org, exposed CI dashboards..., or build artifacts/images are reachable' clause, matching the top anchor.

3 / 3

Trigger Term Quality

Covers natural terms a user would say — 'CI/CD pipeline vulnerabilities', 'public GitHub/GitLab org', 'exposed CI dashboards (Jenkins/TeamCity/Drone/Argo)', 'build artifacts/images' — alongside the domain jargon. The breadth of natural product/tool names keeps it at the top anchor despite some insider shorthand.

3 / 3

Distinctiveness Conflict Risk

The CI/CD pipeline exploitation niche with specific trigger conditions (public GitHub/GitLab org, exposed CI dashboards, reachable artifacts) is clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
elementalsouls/Claude-BugHunter
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.