pubmed-verifier@7.2.0
VERIFIED· install onlyPublisher claims: "Reference checker for AI-fabricated citations: batch-verify PMIDs against PubMed and catch the hallucination existence checks miss — a REAL PMID pointing to a DIFFERENT paper. Five-state citation verification (correct / mismatch / partial / invalid / unknown), citation-context parsing, Crossref DOI cross-check, retraction detection (capped at partial), correct-PMID suggestion, arXiv ID verification, plain-text reference list parsing, formatted reference lists (GB/T 7714 / Vancouver / APA / AMA / Harvard / Chicago), OpenAlex DOI fallback for non-Crossref registries, Chinese-reference title search, CSV/JSON claims, HTML/JSON/text reports. Four data sources: NCBI, Europe PMC fallback, Crossref, OpenAlex. Network failures are honestly reported as unverified, never as "not found". Zero dependencies, runs fully local. Triggers: verify PMIDs, check citations, citation audit, reference check, citation check, batch verify references, AI hallucination detection, verify DOI, DOI check, citation formatting, reference formatter, GB/T 7714." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What changed since 7.0.0
vet-skills diff pubmed-verifier 7.0.0 7.2.0In the sandbox, this version reached for nothing 7.0.0 did not. Compared from the two recorded runs, not from source.
7.0.0 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
| `examples/refs.sample.txt` / `refs_list.sample.txt` | Sample inputs for `--parse-text` (inline-ID routing + a title-only entry) |Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# is echoed as http://user:****@host:port so paste-safe sharing worksFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.python3 scripts/verify_pmids.py --claims-file claims.csv --suggest --output report.htmlFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.python3 verify_pmids.py --claims-file claims.json --output report.htmlFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.# v4.2.0: mask credentials — a proxy URL like http://user:pass@host:portFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.