cve

Known CVE exploitation — fingerprint CMS/framework/plugin version, look up CVE candidates via cve_lookup, retrieve PoCs via cve_poc_lookup, adapt the public exploit to the target, and confirm RCE. Use whenever the challenge tag is `cve`, recon fingerprinted a versioned service, or the challenge name hints at known vulnerable software (WordPress, Joomla, Apache Struts, Spring4Shell, Log4j, etc.).

Quality

90%

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

88%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 highly actionable, well-sequenced exploit methodology with executable commands, mandatory validation checkpoints, and clear feedback loops. Slight room to tighten prose and to split CMS-specific fingerprinting into reference files now that no bundle exists.

Suggestions

Trim editorial justification sentences (e.g. 'The free-form web search fallback is slower and produces stale leads') — the preceding mandatory-tool rule already conveys the instruction.

Move the ~30-entry WordPress plugin readme sweep list into a references file (e.g. references/wp-plugins.txt) and reference it from Step 1, improving progressive disclosure and token efficiency.

Consider extracting the per-CMS fingerprint blocks (WordPress/Joomla/Drupal) into a references/recon-by-cms.md so SKILL.md reads as a lean overview pointing one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly lean, assuming Claude's competence with no concept padding, but a few editorial sentences ('The free-form web search fallback is slower and produces stale leads', 'msfconsole is heavy and breaks the bash-output budget') could be trimmed without losing the instruction.	4 / 5
Actionability	Copy-paste-ready bash throughout — curl/nmap/wpscan commands, a working plugin-readme enumeration loop, and three full PoC-adaptation patterns (curl one-shot, python script, Metasploit-to-curl) with placeholder substitution spelled out.	5 / 5
Workflow Clarity	A clear six-step sequence with explicit validation checkpoints (Step 1 'MUST have at least one <software>@<version>', Step 3 'Version sanity-check is MANDATORY'), a decision-tree feedback loop, and a 3-strike cross-CVE pacing rule for error recovery.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections, but the skill is a single ~190-line file with no bundle; the long WordPress plugin enumeration list and per-CMS fingerprint blocks could live in reference files to keep SKILL.md a leaner overview.	4 / 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 tight, trigger-rich description that names a concrete multi-step action chain and gives explicit 'use when' conditions tied to specific software products. Trigger-term coverage is strong but slightly short of fully comprehensive.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions — 'fingerprint CMS/framework/plugin version', 'look up CVE candidates via cve_lookup', 'retrieve PoCs via cve_poc_lookup', 'adapt the public exploit to the target', 'and confirm RCE' — covering the full CVE workflow comprehensively with no gaps.	5 / 5
Completeness	Explicitly answers both 'what' (the five-step exploitation chain) and 'when' ('Use whenever the challenge tag is `cve`, recon fingerprinted a versioned service, or the challenge name hints at known vulnerable software') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords including 'cve', 'known vulnerable software', and specific product names (WordPress, Joomla, Apache Struts, Spring4Shell, Log4j), but a few common trigger synonyms a user might say (e.g. 'exploit', '0day', 'RCE') are absent from the description itself.	4 / 5
Distinctiveness Conflict Risk	A clear niche — known-CVE exploitation gated by the dedicated cve_lookup/cve_poc_lookup tools and version-fingerprint triggers — with minimal overlap risk against generic attack-class skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/exploit/web/cve/SKILL.md
Commit: 0cf691e

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.