CtrlK
BlogDocsLog inGet started
Tessl Logo

hunt-nosqli

Hunt NoSQL Injection — MongoDB operator injection ($where, $regex, $gt, $ne), CouchDB, Redis command injection, auth bypass via NoSQLi, data dump. Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages.

75

Quality

93%

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

87%

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

A dense, highly actionable reference dominated by concrete payloads and clear phasing, with strong conciseness and self-contained organization. The only gap is the absence of explicit error-recovery feedback loops around destructive Redis operations, which caps workflow clarity.

Suggestions

Add an explicit validate→fix→retry feedback loop for the destructive Redis operations (e.g., confirm SLAVEOF/CONFIG SET succeeded, handle write-permission failures, retry with an alternate payload) to raise workflow clarity.

For the time-based blind injection phase, specify how to interpret a failed/ambiguous delay (e.g., retry with a larger threshold or confirm via a second payload) as a checkpoint rather than only the success signal.

Flag the 'flushall' Redis payload as destructive with a warning to avoid accidental data destruction during testing.

DimensionReasoningScore

Conciseness

The body is lean — mostly executable curl commands, payload tables, and minimal commentary — and assumes Claude's competence without explaining what NoSQL or MongoDB is. Every token earns its place.

3 / 3

Actionability

Fully executable, copy-paste-ready curl commands with real operator payloads (e.g. '{"username": {"$gt": ""}, "password": {"$gt": ""}}', array-notation URLs, gopher:// Redis payloads) across all six phases.

3 / 3

Workflow Clarity

Phases are clearly sequenced and a Validation section with confirmatory checkpoints exists, but destructive/batch operations (Redis 'flushall', 'CONFIG SET', 'SLAVEOF') lack explicit validate→fix→retry feedback loops, which the rubric caps at 2 for such operations.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; the single file is well-organized into clearly labeled sections (Attack Surface Signals, phased methodology, Bypass/Chain tables, Validation), which satisfies the simple-skill allowance for a 3.

3 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that concisely states concrete capabilities and pairs them with explicit 'Use when' triggers grounded in natural stack/error signals. No vagueness or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete attack actions — 'MongoDB operator injection ($where, $regex, $gt, $ne)', 'CouchDB', 'Redis command injection', 'auth bypass via NoSQLi', 'data dump' — matching the anchor for naming several specific actions.

3 / 3

Completeness

Explicitly answers both what ('Hunt NoSQL Injection ... auth bypass via NoSQLi, data dump') and when ('Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages').

3 / 3

Trigger Term Quality

Natural trigger terms users would say are present: 'MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages', giving good coverage of common phrasings rather than jargon.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to NoSQL injection with database-specific triggers (MongoDB/Mongoose, CouchDB, Redis), making it clearly distinguishable from SQL-injection or general web-testing skills and unlikely to misfire.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
elementalsouls/Claude-BugHunter
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.