CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

security-bounty-hunter

Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings. Use when hunting reportable, remotely reachable vulnerabilities in a repository.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/security-bounty-hunter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

The body is a strong example of an instruction-only skill: token-efficient, dense with concrete triage heuristics, and capped with an explicit quality gate that prevents weak submissions. The only notable gaps are the absence of error-recovery feedback loops in the workflow and directional (rather than fully concrete) phrasing in a few workflow steps.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: the in-scope patterns are a dense CWE/impact table with zero padding, there is no explanation of what SSRF or deserialization is, and the skip list, workflow, and quality gate are all terse imperatives. Every section earns its place.

5 / 5

Actionability

There is concrete, executable guidance — a copy-paste 'semgrep --config=auto' command, explicit manual filter rules, a fill-in report template, and a quality-gate checklist. However, several core workflow steps ('Read the real code path end to end', 'Prove user control reaches a meaningful sink') are directional guidance rather than executable instructions, leaving minor gaps.

4 / 5

Workflow Clarity

The 7-step workflow is clearly sequenced and includes validation checkpoints ('Confirm exploitability and impact with the smallest safe PoC', 'Check for duplicates') plus an explicit Quality Gate checklist before submission. It falls short of a 5 because there is no error-recovery feedback loop, e.g. what to do when the PoC fails or a duplicate is found.

4 / 5

Progressive Disclosure

The skill is a self-contained single file with well-organized sections (When to Use, In-Scope Patterns, Skip These, Workflow, Report Structure, Quality Gate) and no bundle files or dangling references. At ~92 lines it exceeds the under-50-line simple-skill threshold, and the pattern table or report template could plausibly live in reference files, so structure is good but not exemplary.

4 / 5

Total

17

/

20

Passed

Description

62%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 is well-constructed: it clearly states what the skill does, includes an explicit 'Use when...' clause, and is appropriately concise with a distinct bounty-hunting niche. Its main weaknesses are limited trigger-term coverage (missing natural user phrases like 'audit this repo', 'responsible disclosure', or platform names) and a when-clause that is largely redundant with the what-statement rather than adding concrete trigger situations.

Suggestions

Add natural trigger synonyms users would actually say, e.g. 'Use when the user asks to audit a repo for vulnerabilities, prepare a responsible-disclosure or HackerOne/Huntr submission, or asks whether a finding is bounty-worthy.'

Differentiate the when-clause from the what-statement by naming distinct triggering situations (e.g. 'when triaging semgrep/static-analysis output for reportable findings' or 'when preparing a CVE or bounty report') instead of restating 'hunting remotely reachable vulnerabilities'.

Name one or two more concrete capabilities in the what-statement (e.g. triaging static-analysis findings, drafting submission-ready reports) to broaden action coverage.

DimensionReasoningScore

Specificity

The description names the domain ('exploitable, bounty-worthy security issues in repositories') and a concrete focus ('remotely reachable vulnerabilities that qualify for real reports'), plus an exclusion ('noisy local-only findings'), but presents only one real action — hunting/triage — rather than several specific actions. It sits between the '1-2 concrete actions, not comprehensive' and 'several specific actions' anchors, closer to the former.

3 / 5

Completeness

Both the 'what' ('Hunt for exploitable, bounty-worthy security issues...') and an explicit 'Use when...' clause are present, so it clears the cap for a missing when-clause. However, the when-clause ('Use when hunting reportable, remotely reachable vulnerabilities in a repository') largely restates the what rather than naming distinct trigger situations, so it does not reach the level-5 anchor of concrete, differentiated trigger phrases.

4 / 5

Trigger Term Quality

It includes relevant keywords ('bounty', 'security issues', 'vulnerabilities', 'repository') but misses common natural variations users would say, such as 'find security bugs', 'audit this repo', 'responsible disclosure', 'HackerOne', or 'CVE'. This matches the anchor 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The bounty-hunting focus ('bounty-worthy', 'qualify for real reports') carves out a clear niche that is mostly distinct from generic code-review or best-practices skills. Minor overlap risk remains with a general security-audit skill, keeping it below the 'clear niche, minimal conflict risk' anchor.

4 / 5

Total

14

/

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

affaan-m/ECC

Path

skills/security-bounty-hunter/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.