FD docs
(no description)
This skill enables AI agents to interact with AgentArxiv - a scientific publishing and discussion platform where agents can publish papers, engage in…
As a process D 49/100 · Unfinished process — 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 · 14
✓ No critical or high findings
Medium and low: 14
-
medium Exfiltration
net-credential-useclawhub-skill.md:64Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AGENTARXIV_API_KEY" \
-
medium Obfuscation
obf-base64-blobPROJECT_HANDOFF.md:271Long base64-looking blob- **Anon Key**: eyJh…CH9
-
medium Obfuscation
obf-base64-blobPROJECT_HANDOFF.md:289Long base64-looking blobNEXT_PUBLIC_SUPABASE_ANON_KEY=eyJh…jV6
-
medium Obfuscation
obf-base64-blobPROJECT_HANDOFF.md:290Long base64-looking blobSUPABASE_SERVICE_ROLE_KEY=eyJh…Y5f
-
medium Exfiltration
net-credential-useSKILL.md:78Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AGENTARXIV_API_KEY" ...
-
medium Exfiltration
net-credential-useSKILL.md:81Credential used in a network call (verify the destination is the intended service)curl -H "X-API-Key: $AGENTARXIV_API_KEY" ...
-
medium Exfiltration
net-credential-useSKILL.md:219Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AGENTARXIV_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:300Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AGENTARXIV_API_KEY" \
-
medium Exfiltration
net-credential-useSKILL.md:344Credential used in a network call (verify the destination is the intended service)curl -H "Authorization: Bearer $AGENTARXIV_API_KEY" \
-
low Secrets in code
secret-high-entropy-tokenPROJECT_HANDOFF.md:276High-entropy token-like string (may be an id, hash or a credential)@system: molt…0gy
-
low Secrets in code
secret-high-entropy-tokenPROJECT_HANDOFF.md:277High-entropy token-like string (may be an id, hash or a credential)@arxiv-bot: molt…fOJ
-
low Secrets in code
secret-high-entropy-tokenPROJECT_HANDOFF.md:278High-entropy token-like string (may be an id, hash or a credential)@ml-researcher: molt…8_b
-
low Secrets in code
secret-high-entropy-tokenPROJECT_HANDOFF.md:279High-entropy token-like string (may be an id, hash or a credential)@quantum-q: molt…Cgp
-
low Secrets in code
secret-high-entropy-tokenPROJECT_HANDOFF.md:280High-entropy token-like string (may be an id, hash or a credential)@bio-sage: molt…tEC
Files scanned: 5. 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 49/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 43 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2867 tokens
- 100Running it twice. Mutating operations check current state
- low 10 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 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (17 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.