supply-chain-attack-recon

External recon for software supply-chain attack surface — package-namespace squatting candidates, dependency-confusion vulnerabilities, GitHub Actions injection openings, container image registry exposure, SBOM mining, internal-package-name leakage, and CI/CD configuration exposure. Reconnaissance and identification ONLY — actual package publishing / typosquat attacks are EXTERNAL-OFFENSIVE and require explicit written sign-off because they can affect the entire npm/PyPI ecosystem. Use when the target has a public GitHub org, when their build artifacts/SBOMs are reachable, when their docker images are on Docker Hub/GHCR, or when you find internal package names in their JS bundles.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

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

The body is highly actionable and well-sequenced with good validation checkpoints, but it is padded with an encyclopedic 12-case historical catalogue that largely re-tells incidents Claude already knows and should live in a separate reference file. Tightening that section and externalizing it would raise both conciseness and progressive disclosure.

Suggestions

Move the 'Disclosed-case catalogue (citations)' section (cases 1–12) into a references/ file such as references/case-catalogue.md, keeping only the coverage-map table and a one-line pointer in SKILL.md — this restores conciseness and enables one-level-deep progressive disclosure.

In the inline body, condense each case to its recon takeaway plus a single reference link instead of Flow/Root cause/Impact narrative, which largely re-explains widely known incidents.

Extract the long 'Related Skills & Chains' bridge prose into a short bulleted list or a references/ file so the core recon workflow stays the focal point of SKILL.md.

Dimension	Reasoning	Score
Conciseness	The 10 recon steps are lean and actionable, but the ~250-line disclosed-case catalogue narrates well-known incidents (SolarWinds, Log4Shell, MOVEit, XZ Utils, event-stream) with Flow/Root cause/Impact prose Claude already knows, so the body could be tightened significantly.	2 / 3
Actionability	Every step ships copy-paste-ready bash (gh/curl/jq/docker), concrete GitHub Actions injection regexes, a tooling table, and severity tables — fully executable and specific rather than described.	3 / 3
Workflow Clarity	A clear 10-step sequence with explicit validation: severity calibration in Step 4 ('A 404 on registry without supporting context is INFORMATIONAL only'), a 'What constitutes a deliverable finding' checklist, and DO/DO-NOT guardrails for batch and risky operations.	3 / 3
Progressive Disclosure	There are no bundle files (references/scripts/assets absent) and the body is monolithic; the large case catalogue, related-skills chains, and coverage maps are content that should be split into a reference file rather than kept inline.	2 / 3
	Total	10 / 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 strong: it states concrete capabilities in third person, includes an explicit 'Use when…' trigger clause, and carves out a distinctive niche. It also clearly scopes the offensive boundary, which aids correct triggering. No weaknesses warrant a sub-maximal score on any dimension.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'package-namespace squatting candidates, dependency-confusion vulnerabilities, GitHub Actions injection openings, container image registry exposure, SBOM mining, internal-package-name leakage, and CI/CD configuration exposure' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (external recon for the supply-chain attack surface, enumerating seven activities) and when via a clear 'Use when the target has a public GitHub org…' clause, matching the top anchor.	3 / 3
Trigger Term Quality	Natural domain terms a user would say are well covered: 'public GitHub org', 'build artifacts/SBOMs', 'docker images on Docker Hub/GHCR', 'internal package names in their JS bundles', plus 'dependency-confusion' and 'typosquat'.	3 / 3
Distinctiveness Conflict Risk	Supply-chain attack recon is a clear niche with specific, narrow triggers (public GitHub org, reachable SBOMs, public Docker images, internal names in JS bundles) unlikely to conflict with generic skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (575 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: elementalsouls/Claude-BugHunter
Path: skills/supply-chain-attack-recon/SKILL.md
Commit: 6b9c96e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.