SKILLEMALL.ai
GitHub ↗ RU Sign in

CD lambda-labs

On-demand GPU cloud instances for ML training.

NousResearch/hermes-agent Hermes author: NousResearch MIT 3 files body ≈ 2 918 tokens Open the sourcegithub.com↗ analyzed 35 h ago

On-demand GPU cloud instances for ML training.

As a process D 40/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
C
63/100
safety, quality, tests
Safety 60%
49
Quality 40%
83
Run on models
none yet
Process rating
D
40/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
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.

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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

    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 Dangerous commands cmd-shell-rc references/advanced-usage.md:610
      Writes to a shell startup file
      echo 'export HF_TOKEN="..."' >> ~/.bashrc
    • medium Exfiltration net-credential-use references/troubleshooting.md:12
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Exfiltration net-credential-use references/troubleshooting.md:50
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Exfiltration net-credential-use references/troubleshooting.md:82
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Dangerous commands cmd-pipe-to-shell references/troubleshooting.md:148
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      wget -nv -O- https://lambdalabs.com/install-lambda-stack.sh | sh -
      vendor-host
    • medium Dangerous commands cmd-pipe-to-shell references/troubleshooting.md:196
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      wget -nv -O- https://lambdalabs.com/install-lambda-stack.sh | sh -
      vendor-host
    • medium Exfiltration net-credential-use references/troubleshooting.md:479
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Exfiltration net-credential-use SKILL.md:225
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Exfiltration net-credential-use SKILL.md:232
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • medium Exfiltration net-credential-use SKILL.md:245
      Credential used in a network call (verify the destination is the intended service)
      curl -u $LAMBDA_API_KEY: \
    • low Exfiltration read-dotenv references/advanced-usage.md:607
      Reads a .env file
      source .env

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "dependencies"

    Process rating: all ten parameters 40/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 60Tools and files. Uses tools (web, python, node) that frontmatter does not declare
    • 60Consistency. The Hermes dialect needs category and tags
    • 100Steps. 66 steps
    • 100Execution cost. Instruction body is 2918 tokens
    • low 17 top-level sections: this looks like several domains in one skill

    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 46: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • +2Single-language instructions
    • +4Structure: 60 headings
    • +3Step-by-step instructions: 66 items
    • +4Has examples (29 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.