DC zotero-enhanced
Zotero library management with PDF metadata auto-fetch (Crossref/arXiv), item search, file read, and note management. Supports cloud and WebDAV storage.
Zotero library management with PDF metadata auto-fetch (Crossref/arXiv), item search, file read, and note management.
As a process C 53/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
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.
How to improve
- 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 · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
net-credential-usescripts/add_to_zotero_enhanced.sh:383Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -T "$PROP_FILE" "$WEBDAV_TARGET_URL"
-
medium Exfiltration
net-credential-usescripts/add_to_zotero_enhanced.sh:386Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -T "$ZIP_FILE" "$WEBDAV_TARGET_URL"
-
medium Exfiltration
net-credential-usescripts/add_to_zotero_universal.sh:517Credential used in a network call (verify the destination is the intended service)HTTP_PROP=$(curl -s -o /dev/null -w "%{http_code}" -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" \ -
medium Exfiltration
net-credential-usescripts/add_to_zotero_universal.sh:519Credential used in a network call (verify the destination is the intended service)HTTP_ZIP=$(curl -s -o /dev/null -w "%{http_code}" -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" \ -
medium Exfiltration
net-credential-usescripts/add_to_zotero.sh:133Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -T "$PROP_FILE" "$WEBDAV_TARGET_URL"
-
medium Exfiltration
net-credential-usescripts/add_to_zotero.sh:136Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -T "$ZIP_FILE" "$WEBDAV_TARGET_URL"
-
medium Exfiltration
net-credential-usescripts/read_universal.sh:140Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -o "$ZIP_PATH" "$WEBDAV_SOURCE_URL"
-
medium Exfiltration
net-credential-usescripts/read_universal.sh:179Credential used in a network call (verify the destination is the intended service)curl -s -f -H "Zotero-API-Key: $ZOTERO_API_KEY" -o "$PDF_PATH" "$DOWNLOAD_URL"
-
medium Exfiltration
net-credential-usescripts/read.sh:79Credential used in a network call (verify the destination is the intended service)curl -s -f -u "$ZOTERO_WEBDAV_USER:$ZOTERO_WEBDAV_PASS" -o "$LOCAL_ZIP_PATH" "$WEBDAV_SOURCE_URL"
-
low Exfiltration
net-credential-useSKILL.md:357Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)- **Improvement**: WebDAV upload URL uses explicit filename (`$WEBDAV_BASE_URL/${ATTACH_KEY}.prop`) instead of relying on curl's trailing-slash filename appending behavior.quoted
Files scanned: 16. 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") - note
edit-residuethe text marks something as outdated (lines 77, 157, 296, 343): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 53/100
- 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. 30 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4807 tokens
- 85Steps. 125 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- 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)
- +2Single-language instructions
- +3Description length 152: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 125 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +3All 11 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.