CtrlK
BlogDocsLog inGet started
Tessl Logo

competition-ssrf-metadata-pivot

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for SSRF reachability, internal route probing, metadata-service access, credential pivoting, and token-to-accepted-privilege chains. Use when the user asks to trace SSRF sources, internal hosts, metadata endpoints, link-local tokens, service-account credentials, or explain how a server-side fetch edge turns into accepted access. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

72

Quality

91%

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

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 instruction-only skill body: concise, actionable analysis checklists, a clear three-stage workflow with a handoff rule, and a single verified one-level-deep reference. Minor room to add explicit verification checkpoints and a concrete payload/example to reach top actionability and workflow-clarity scores.

Suggestions

Add an explicit validation/verification checkpoint in the workflow, e.g. confirm acceptance proof ('verify the recovered token is actually accepted by the downstream service') before declaring the chain decisive.

Include one concrete minimal SSRF-to-accepted-access payload or request shape as an example to push actionability toward copy-paste-ready.

Make the reduction step's success criterion explicit (what evidence proves the decisive edge) so the sequence ends on a clear checkpoint.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanation of concepts Claude already knows ('Record source primitive: URL parameter, webhook, image fetcher, importer, proxy endpoint, or backend callback'); every token earns its place, so it sits at 5 rather than 4.

5 / 5

Actionability

Concrete, specific guidance ('Record request method, URL construction, header behavior, redirects, DNS or host overrides, and response shaping before mutation'); not 5 because it lacks copy-paste-ready payload/example specifics, and not 3 because the directions are concrete and directly executable for an analysis skill (absence of code is fine for instruction-only).

4 / 5

Workflow Clarity

Clear numbered Quick Start plus a three-stage Workflow with sequencing and an explicit handoff rule ('If the task becomes mostly cloud identity policy analysis, hand off...'); not 5 because validation checkpoints are implicit ('Reproduce the smallest SSRF-to-accepted-access path') rather than explicit validate/verify gates, and not 3 because the sequence and reduction step are clearly defined. No destructive/batch cap applies since this is read-only probing/evidence gathering.

4 / 5

Progressive Disclosure

Concise overview body with a single clearly-signaled one-level reference ('Load `references/ssrf-metadata-pivot.md` for SSRF checklists, metadata pivots, and evidence packaging') whose target file exists; not 4 because navigation is clean and appropriately split.

5 / 5

Total

18

/

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.

A strong, specific description that clearly states what the skill does and when to use it, with concrete trigger terms and explicit upstream routing that sharply limits conflict risk. The only minor gap is slight synonym/extension coverage in trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('SSRF reachability, internal route probing, metadata-service access, credential pivoting, and token-to-accepted-privilege chains') with comprehensive coverage; not below 5 since coverage is thorough and not 4 because nothing material is missing.

5 / 5

Completeness

Explicitly answers both 'what' (the CTF-sandbox SSRF/pivot workflow) and 'when' ('Use when the user asks to trace SSRF sources...') with concrete trigger phrases; not 4 because both halves are explicit and specific.

5 / 5

Trigger Term Quality

Good natural-keyword coverage ('SSRF sources, internal hosts, metadata endpoints, link-link tokens, service-account credentials'); not 5 because it omits some common synonyms and file/protocol extensions, and not 3 because the phrases users would actually say are well represented.

4 / 5

Distinctiveness Conflict Risk

Clear niche with explicit routing ('Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here') minimizing conflict risk; not 4 because the boundary is unambiguous.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zhaoxuya520/reverse-skill
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.