CB academic-talon
🎓 Full-stack academic research assistant - Search papers → Extract publication-ready BibTeX (header) → Full TEI XML document structure parsing (via GROBID) → Archive to Zotero → Serve local PDFs. Fixed arXiv AND search semantics, generates conference/journal-standard BibTeX, auto-creates Zotero collections, enables deep document understanding via GROBID structured parsing.
As a process B 73/100 · Nearly there — weak spots: progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
-
high Secrets in code
meta-credential-files.envCredential / dotenv files bundled with the skill (1).env
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyscripts/zotero_archiver.py:434Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 73/100
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 55 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3578 tokens
- 100Running it twice. Mutating operations check current state
- low 11 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)
- -2localhost URLs: will not work for another user
- -239 emoji in the instructions: noise for the model
- -33 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 376: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 55 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.