hunt-misc

Hunting skill for misc vulnerabilities. Built from 225 public bug bounty reports. Use when hunting misc on any target.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/hunt-misc/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable payloads and a well-sequenced methodology backed by explicit validation gates. Its main weaknesses are verbosity from overlapping sections (root causes, scenarios, chains) and a monolithic structure with no progressive disclosure into bundle files despite the length.

Suggestions

Deduplicate overlapping content: Common Root Causes, Real Impact Examples, and Chains & Compositions restate the same primitives; merge the scenario narratives into the chain entries or drop the standalone scenarios.

Offload the large Payload & Detection Patterns and Chains sections into reference files under references/ (e.g. PAYLOADS.md, CHAINS.md) and signal them one level deep from SKILL.md to improve progressive disclosure.

Trim prose around code blocks to only what Claude would not already infer from the commands, tightening conciseness toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	The body is densely operational (curl, ruby, grep, dig commands) rather than explaining basic concepts, but at ~330 lines it carries redundancy: Common Root Causes, Real Impact Examples, and Chains & Compositions restate the same primitives, so it is 'mostly efficient but could be tightened' rather than lean.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands (curl invocations, ruby -e one-liners, grep patterns, dig checks) with concrete parameters, matching the score-3 'fully executable code/commands; specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A numbered 12-step 'Step-by-Step Hunting Methodology' is sequenced, with explicit validation checkpoints: 'Gate 0 Validation' (three questions), the 'Body-Diff Rule', and 'Marker Discipline', matching the score-3 'clear sequence with explicit validation steps; checklists' anchor.	3 / 3
Progressive Disclosure	The skill is well-organized into clear sections but is a monolithic ~330-line SKILL.md with no bundle files (references/scripts/assets are absent), so payloads, chains, and root causes that should be split into separate reference files are inline, fitting the score-2 'content that should be separate is inline' anchor rather than a one-level-deep reference structure.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 answers both what and when with an explicit trigger, but the action set is generic ('hunting misc') and the 'misc' category is a catch-all that risks overlapping with more specific sibling hunting skills. Specificity and trigger-term quality are the weak points.

Suggestions

Replace the generic action 'hunting misc' with 2-3 concrete actions, e.g. 'Finds access-control failures, info disclosure, and session/auth logic bugs in SaaS and multi-tenant targets'.

Broaden trigger terms beyond the jargon word 'misc' to natural phrases a user would say, such as 'privilege escalation', 'invitation or SSO logic bugs', or 'post-removal access'.

Narrow the distinctiveness scope so it does not read as overlapping with hunt-saml / hunt-auth-bypass / hunt-ato, e.g. by stating it covers residual access-control and misconfig classes not handled by those skills.

Dimension	Reasoning	Score
Specificity	Quotes "Hunting skill for misc vulnerabilities" name the domain and a concrete action (hunting) but do not list multiple specific concrete actions, falling short of the score-3 'multiple specific concrete actions' anchor and above the vague score-1 anchor.	2 / 3
Completeness	It states what it does ("Hunting skill for misc vulnerabilities") and an explicit when clause ("Use when hunting misc on any target"), satisfying the score-3 anchor requiring both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	The trigger "Use when hunting misc on any target" provides a natural phrasing, but "misc" is generic jargon with thin coverage of variations users would say, matching 'some relevant keywords but missing common variations' rather than the rich score-3 coverage.	2 / 3
Distinctiveness Conflict Risk	"misc vulnerabilities" is a residual catch-all category that overlaps with sibling skills (hunt-saml, hunt-auth-bypass, hunt-ato are all referenced in the body), so it is 'somewhat specific but could still overlap' rather than a clearly distinct niche.	2 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: elementalsouls/Claude-BugHunter
Path: skills/hunt-misc/SKILL.md
Commit: 6b9c96e

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.