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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/supply-chain-attack-recon/SKILL.md

Quality

Content

60%Weight 40%Scale 1-5

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

The recon workflow is highly actionable and clearly sequenced with strong validation discipline around the external-offensive boundary, but the skill is a monolithic 649-line document that inlines a large case-history reference section instead of splitting it into a reference file, hurting token efficiency and progressive disclosure.

Suggestions

Move the 'Disclosed-case catalogue' (cases 1–12) into a separate references/ file (e.g. CASES.md) and replace it in SKILL.md with a brief table mapping each recon step to its anchoring case, linking out for full writeups.

Extract the 'Real-world references' list and 'Tooling' table into a reference file or keep only the tool names inline, since the case-specific references already live in the catalogue.

Add an explicit per-step validation checkpoint for the destructive/offensive steps (e.g., 'before listing a typosquat candidate, confirm it is unclaimed AND in an active build') to strengthen the feedback loops.

Dimension	Reasoning	Score
Conciseness	The ~649-line body inlines a ~170-line 'Disclosed-case catalogue' of detailed incident writeups (flow/root cause/impact/references per case) that is reference material better kept out of the always-loaded SKILL.md, making it noticeably verbose despite the lean recon steps.	2 / 5
Actionability	Every step provides copy-paste-ready bash with real gh/curl/jq/docker commands and concrete grep patterns, and the tooling and severity tables give specific executable guidance covering the common cases.	5 / 5
Workflow Clarity	An explicit 11-step sequence is clearly laid out with severity-calibration guidance, an anti-patterns section, and a 5-part 'What constitutes a deliverable finding' checklist that acts as validation for the external-offensive boundary; minor gap is the lack of per-step validate→fix→retry loops.	4 / 5
Progressive Disclosure	No bundle files exist and all content — including the large case catalogue that clearly belongs in a separate reference file — is inlined in SKILL.md, with no one-level-deep external references for the bulk detail.	2 / 5
	Total	13 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 specific, well-triggered, and clearly scoped, explicitly answering both what the skill does and when to use it with concrete natural-language triggers. Only minor weakness is the absence of file-extension terms in the trigger list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — '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' — giving comprehensive coverage of the attack surface.	5 / 5
Completeness	Explicitly answers 'what' (the recon capabilities) and 'when' via a concrete 'Use when the target has a public GitHub org... build artifacts/SBOMs are reachable... docker images on Docker Hub/GHCR... internal package names in their JS bundles' trigger clause.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('public GitHub org', 'build artifacts/SBOMs', 'docker images on Docker Hub/GHCR', 'JS bundles', 'npm/PyPI') with synonyms and platform names, but no file extensions like .npmrc or package.json that users might mention.	4 / 5
Distinctiveness Conflict Risk	Clear niche (external software supply-chain attack-surface recon) with distinct, specific triggers and an explicit scope boundary (recon-only vs external-offensive), minimizing overlap with neighboring skills.	5 / 5
	Total	19 / 20 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 (649 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: 0ce18ba

Reviewed: 1 day 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.