FC ethosmolt
(no description)
As a process C 52/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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".
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Add a description to the frontmatter: without it the skill never triggers.
- 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 · 16
✓ No critical or high findings
Medium and low: 16
-
medium Exfiltration
net-credential-useSKILL.md:26Credential used in a network call (verify the destination is the intended service)--private-key $PRIVATE_KEY --rpc-url https://rpc.monad.xyz
-
medium Exfiltration
net-credential-useSKILL.md:103Credential used in a network call (verify the destination is the intended service)--private-key $PRIVATE_KEY --rpc-url https://rpc.monad.xyz
-
medium Exfiltration
net-credential-useSKILL.md:109Credential used in a network call (verify the destination is the intended service)--private-key $PRIVATE_KEY --rpc-url https://rpc.monad.xyz
-
medium Exfiltration
net-credential-useSKILL.md:115Credential used in a network call (verify the destination is the intended service)--private-key $PRIVATE_KEY --rpc-url https://rpc.monad.xyz
-
medium Exfiltration
net-credential-useSKILL.md:121Credential used in a network call (verify the destination is the intended service)--private-key $PRIVATE_KEY --rpc-url https://rpc.monad.xyz
-
medium Obfuscation
obf-base64-blobSKILL.md:128Long base64-looking blobAnon Key: eyJh…lQQ
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:15High-entropy token-like string (may be an id, hash or a credential)ERC-8004 Identity Registry 0x80…432
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:16High-entropy token-like string (may be an id, hash or a credential)ERC-8004 Reputation Registry 0x80…b63
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:24High-entropy token-like string (may be an id, hash or a credential)cast send 0x80…432 \
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:30High-entropy token-like string (may be an id, hash or a credential)cast call 0x80…432 \
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:100High-entropy token-like string (may be an id, hash or a credential)cast send 0x80…b63 \
-
low Obfuscation
obf-base64-blobSKILL.md:130Long base64-looking blob (quoted — discussed, not commanded)-H "apikey: eyJh…4wl
quoted -
low Secrets in code
secret-labelled-tokenSKILL.md:130Labelled token / key literal (vendor format unknown — verify it is not a live credential) (quoted — discussed, not commanded)-H "apikey: eyJh…4wl
quoted -
low Secrets in code
secret-password-literalSKILL.md:130Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)-H "apikey: eyJh…4wl
quoted -
low Obfuscation
obf-base64-blobSKILL.md:131Long base64-looking blob (quoted — discussed, not commanded)-H "Authorization: Bearer eyJh…V9C
quoted -
low Obfuscation
obf-base64-blobSKILL.md:225Long base64-looking blob (quoted — discussed, not commanded)export SUPABASE_ANON_KEY="eyJh…V9C
quoted
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2647 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (12 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 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 6 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.