SKILLEMALL.ai
GitHub ↗ RU Sign in

CC github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent Hermes author: NousResearch MIT 17 files · 1 script body ≈ 510 tokens Open the sourcegithub.com↗ analyzed 2 d ago

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGitHubSoftware developmentData and analyticstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
C
66/100
safety, quality, tests
Safety 60%
61
Quality 40%
73
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.
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 · 11

✓ No critical or high findings

Medium and low: 11
  • medium Exfiltration net-credential-use references/auth.md:256
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use references/ci-troubleshooting.md:12
    Credential used in a network call (verify the destination is the intended service)
    curl -sL -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use references/code-review.md:345
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use references/code-review.md:349
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use references/code-review.md:407
    Credential used in a network call (verify the destination is the intended service)
    HEAD_SHA=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use references/github-api-cheatsheet.md:139
    Credential used in a network call (verify the destination is the intended service)
    curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • medium Exfiltration net-credential-use scripts/gh-env.sh:40
    Credential used in a network call (verify the destination is the intended service)
    GH_USER=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
  • low Exfiltration net-credential-use references/auth.md:213
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    > LOGIN=$(curl -s -H "Authorization: token $TOKEN" https://api.github.com/user \
    known service
  • low Exfiltration net-credential-use references/github-api-cheatsheet.md:133
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)
    - Check remaining: `curl -s -H "Authorization: token $GITHUB_TOKEN" https://api.github.com/rate_limit`
    known servicequoted
  • low Exfiltration net-credential-use references/pr-workflow.md:349
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; documentation table row)
    | List my PRs | `gh pr list --author @me` | `curl -s -H "Authorization: token $GITHUB_TOKEN" "https://api.github.com/repos/$OWNER/$REPO/pulls?state=open"` |
    known servicetable
  • low Exfiltration net-credential-use references/repo-management.md:29
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    GH_USER=$(curl -s -H "Authorization: token $GITHUB_TOKEN" https://api.github.com/user | python -c "import sys,json; print(json.load(sys.stdin)['login'])")
    known service

Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill

Process rating: all ten parameters 57/100

  • 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
  • 30Running it twice. 5 mutating operations with no state check
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Tools and files. No external tools needed
  • 100Steps. 7 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Execution cost. Instruction body is 510 tokens

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 53: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +2Single-language instructions
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 7 items
  • +4Reference files are cited in the instructions (10 of 10)
  • +3All 2 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.