CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

supplychain-overview

Supply-chain attack category — dependency confusion, typosquatting, package-registry abuse, build-pipeline poisoning, SBOM manipulation.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/exploit/supplychain/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A tight, well-structured routing skill: lean token budget, executable discovery commands, and genuinely useful authorization/payload decision notes with an explicit checkpoint on the one destructive operation. The only notable gap is the missing registry-availability verification step that would close the dependency-confusion discovery loop.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and every token earns its place: a routing table with concrete load conditions, four copy-paste discovery commands, and decision notes carrying non-obvious operational specifics ("beacon-only payload (DNS callback, HTTPS GET)", "postinstall, setup.py install"). It assumes Claude's competence and explains nothing it already knows.

5 / 5

Actionability

The surface-discovery greps ("grep -hE '\"name\":|\"@.+/\"' package-lock.json yarn.lock pnpm-lock.yaml") are executable and cover npm, pip, Go, and Maven, and the sub-skill load path is concrete. Not anchor 5: the key confirmation step for dependency confusion — checking whether a discovered name is absent from the public registry (e.g. `npm view <pkg>`) — is absent, and the requirements.txt grep matches nearly every line rather than isolating package names.

4 / 5

Workflow Clarity

The flow (run discovery greps → match findings to the sub-skill "When to Load" column → apply decision notes) is discernible, and the one destructive operation (publishing to a public registry) has an explicit validation checkpoint: "Always confirm scope authorization in writing before publishing any package". Not anchor 5: the sequence is never explicitly ordered (the Sub-Skills table precedes Surface Discovery) and there is no verify/loop step after discovery output.

4 / 5

Progressive Disclosure

Under 50 lines, no bundle files needed, cleanly sectioned (Sub-Skills, Surface Discovery, Decision Notes), with one-level-deep external pointers clearly signaled via the "When to Load" column and explicit skill paths. Per the rubric's simple-skill guidance, this earns a 5 on well-organized sections alone.

5 / 5

Total

18

/

20

Passed

Description

66%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.

A specific, well-scoped niche description with strong distinct terminology, but it reads as a taxonomy label rather than a capability statement, and it omits any "Use when..." trigger clause in the description field itself. The rich trigger keywords exist in metadata.when_to_use but are not surfaced where they would count.

Suggestions

Append an explicit trigger clause to the description, e.g. "Use when the target uses npm/PyPI/RubyGems/Cargo/Maven dependencies, private registries, CI build pipelines, or SBOMs," promoting the metadata.when_to_use terms into the description field.

State the skill's action in the description (e.g. "Routes supply-chain attack research to sub-skills and provides lockfile/package-name surface discovery") so the "what" describes capabilities, not just topic areas.

Include ecosystem-specific synonyms (npm, PyPI, cargo, Maven, lockfile) directly in the description to strengthen trigger coverage for users who name the ecosystem rather than the attack technique.

DimensionReasoningScore

Specificity

The description enumerates several concrete, specific areas ("dependency confusion, typosquatting, package-registry abuse, build-pipeline poisoning, SBOM manipulation"), exceeding the 1-2 items of anchor 3. It falls short of anchor 5 because these are domain topics rather than actions — the description never states what the skill actually does (route, dispatch, enumerate).

4 / 5

Completeness

The "what" is clear (a category/routing skill covering five named supply-chain technique areas), but the description field contains no "Use when..." clause or equivalent explicit trigger guidance — "when" is only weakly implied by the topic list. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; the when_to_use metadata exists but sits outside the description field.

3 / 5

Trigger Term Quality

It contains natural terms users would say ("supply-chain", "dependency confusion", "typosquatting", "SBOM", "build-pipeline") giving good keyword coverage per anchor 4. Not anchor 5: ecosystem synonyms users commonly name (npm, PyPI, cargo, .lock files) appear only in metadata.when_to_use, not in the description itself.

4 / 5

Distinctiveness Conflict Risk

The attack framing ("Supply-chain attack category", "typosquatting", "SBOM manipulation") gives a clear niche mostly distinct from other skills. Not anchor 5: the category explicitly overlaps an adjacent CI/build skill (routed to ad/SKILL.md in the body), and generic tokens like "package" and "registry" carry minor conflict risk with benign package-management requests.

4 / 5

Total

15

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/exploit/supplychain/SKILL.md

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.