CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web

Web application exploitation — the primary category skill for all web-based attacks. This is a routing skill: read this first to identify the attack type, then load the appropriate specialized sub-skill for detailed procedures. Covers 11 technique areas across injection, file access, authentication, and API exploitation.

Quality

68%

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/web/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured routing skill: concrete probes, exact sub-skill paths, and an explicit pivot/pacing discipline give it strong actionability and workflow clarity, and the overview-to-sub-skill split is textbook progressive disclosure. Its main weakness is token weight — many routing rows duplicate sub-skill-level technique detail that the router does not need to make a load decision, and a few conventions (PIVOT.md, SUMMARY.md) are referenced without definition.

Suggestions

Trim the 'Covers' column of the routing table to 2-3 word technique labels; move payload-class detail (e.g. blind-sqli's probe-loop specifics, smuggling's CL.TE/TE.CL variants) into the sub-skills, keeping only the 'When to Load' signal in this file.

Define or point to the `exploit/PIVOT.md` and recon `SUMMARY.md` conventions (one line each) so the pivot rule is self-contained rather than assuming external context.

Extend the Quick Detection probes to cover the higher-frequency routed classes with no probe (e.g. IDOR/object-ID check, JWT bearer-token check) so 'Unknown → run probes' is more likely to resolve the route.

DimensionReasoningScore

Conciseness

The routing table, decision flow, and pacing rules are mostly high-signal, but many table rows inline sub-skill detail that belongs in the sub-skills themselves (e.g. blind-sqli's "token-fingerprinting probe loops, arithmetic-multiplication boolean evaluation, hex-encoded literals, exponential-probe binary search"; similarly dense smuggling and crypto rows). Mostly efficient but could be tightened to a leaner when-to-load signal per row.

3 / 5

Actionability

The Quick Detection section gives eight copy-paste-ready curl probes and every table row carries an exact `load_skill("...")` path, which is concrete and executable. Minor gaps remain: probes use a `<TARGET>` placeholder and the pacing rule references `exploit/PIVOT.md` and "recon SUMMARY.md" conventions that are never defined or linked here.

4 / 5

Workflow Clarity

A clear sequence exists (detect via probes → decision flow → load sub-skill), and the Payload Pacing rule supplies explicit feedback thresholds (3 same-class negatives → next bypass class; 3 exhausted classes → pivot) that function as validation checkpoints. Verification of exploitation success is delegated to sub-skills and the referenced system-prompt agent loop rather than restated, leaving a minor checkpoint gap at the router level.

4 / 5

Progressive Disclosure

This is a model router skill: the body is a pure overview whose only depth is one-level-deep, clearly signaled `load_skill` pointers into specialized sub-skills, organized in a scannable table plus a decision tree. No bundle files (references/, scripts/, assets/) exist and none are implied, and the split between overview and detail is exactly where it should be.

5 / 5

Total

16

/

20

Passed

Description

53%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 clearly states what the skill is and does in third person, and its router role is well distinguished from sibling category skills. It is capped by a missing 'Use when' trigger clause, trigger terms that live only in metadata rather than the description, and a stale '11 technique areas' claim that contradicts the 30 sub-skills the body actually routes to.

Suggestions

Add an explicit trigger clause to the description, e.g. 'Use when the target is a web application or web-exposed service — HTTP/HTTPS endpoints, login forms, APIs, cookies, or any web vulnerability class.'

Fix the stale coverage claim: 'Covers 11 technique areas' should match the 30 routed sub-skills (or drop the count and name the major classes: injection, file access, authentication, session/token, API, and request-handling abuse).

Fold a few high-frequency natural trigger terms (SQL injection, XSS, SSRF, deserialization, web shell) into the description itself instead of keeping them only in metadata.when_to_use.

DimensionReasoningScore

Specificity

It names the domain ("Web application exploitation") and 1-2 concrete actions ("identify the attack type, then load the appropriate specialized sub-skill") in third person, but coverage is not comprehensive and the summary claim "Covers 11 technique areas" is stale — the body routes to 30 sub-skills, contradicting the count.

3 / 5

Completeness

The 'what' is clear (a routing/category skill that identifies the attack type and loads a specialized sub-skill), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The description contains some relevant keywords ("web-based attacks", "injection", "file access", "authentication", "API exploitation") but misses the natural terms users would actually say for this domain — SQL injection, XSS, SSRF, web shell — which instead sit in the separate metadata.when_to_use field rather than the description itself.

3 / 5

Distinctiveness Conflict Risk

The niche is explicit ("the primary category skill for all web-based attacks"), making it easy to distinguish from sibling category skills, and its router role is stated. Minor overlap risk remains by design: it will match nearly any web-technique query that its 30 sub-skills also match, relying on the read-this-first convention to resolve.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/exploit/web/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.