SKILLEMALL.ai
GitHub ↗ RU Sign in

CF bounty-hunting

Systematic approach to finding, evaluating, and tracking GitHub bounties and open source opportunities

ClawHub Hermes author: lrg913427-dot v1.0.0 MIT-0 18 files body ≈ 10 157 tokens Open the sourceclawhub.ai↗ analyzed 23 h ago

Systematic approach to finding, evaluating, and tracking GitHub bounties and open source opportunities

As a process F 42/100 · Will not run — References files that are not bundled: scripts/scan-bounties.sh

AnalyzerGitHubObsidianSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
C
70/100
safety, quality, tests
Safety 60%
86
Quality 40%
47
Run on models
none yet
Process rating
F
42/100
Will not run
References files that are not bundled: scripts/scan-bounties.sh
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  3. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  4. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration exfil-read-secret-files references/known-bounty-repos.md:170
    Reads credential / secret files (documentation of a security skill)
    with open(os.path.expanduser('~/.git-credentials')) as f:
    security skill
  • medium Exfiltration exfil-read-secret-files SKILL.md:421
    Reads credential / secret files (documentation of a security skill)
    with open(os.path.expanduser('~/.git-credentials')) as f:
    security skill
  • low Risky intent intent-offensive-security references/known-bounty-repos.md:22
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - **Labels**: `💎 Bounty`, `$X`, `AI agent friendly`, `bug bounty`, `good first issue`, `help wanted`
    detector

A further 3 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 102 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • warning body-long SKILL.md body ≈ 10157 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/scan-bounties.sh

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: scripts/scan-bounties.sh
  • 0Tools and files. 1 referenced file(s) missing: scripts/scan-bounties.sh
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Execution cost. Instruction body is 10157 tokens: crowds the task out of the window
  • 100Steps. 187 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 13 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 102: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • +1No license
  • +2Single-language instructions
  • +4Structure: 69 headings
  • +3Step-by-step instructions: 187 items
  • +4Has examples (22 code blocks)
  • +4Reference files are cited in the instructions (10 of 11)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.

External checks

ClawHub: suspicious
This bounty-hunting skill is mostly coherent as GitHub workflow guidance, but it also directs sensitive credential handling, mailbox access, security-tool workarounds, and ungated public write actions.
LLM: suspicious (high) · 23 Jul 2026