Retraction Watcher
v1.0.0Automatically scan document reference lists and check against Retraction.
⭐ 0· 33·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (scan references for retractions) match the included files and instructions: a Python script that parses citations and queries retraction sources (Crossref, PubMed, Retraction Watch, Open Retractions). No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
SKILL.md and scripts/main.py confine actions to parsing provided documents and calling public retraction APIs. Be aware the workflow sends identifiers/titles to external services (Crossref, PubMed, etc.) for matching; the instructions do not request or access unrelated files, system secrets, or other agent credentials.
Install Mechanism
There is no install spec (instruction-only skill with a packaged script). The code uses standard Python libraries and small third-party packages declared in requirements.txt (dataclasses, pypdf2). Nothing is downloaded from arbitrary URLs or installed from untrusted hosts.
Credentials
The skill requires no environment variables, credentials, or config paths. That is proportional to its function (it queries public APIs). There are no requests for unrelated secrets or broad environment access.
Persistence & Privilege
The skill is not always-enabled and uses default autonomous invocation settings. It does not request permanent system presence or attempt to modify other skills or system-wide agent settings.
Assessment
This package appears coherent for checking citations against retraction sources. If you plan to use it, note that the script will make outbound requests to third-party APIs (Crossref, PubMed, Retraction Watch, Open Retractions) and may transmit DOIs, PMIDs, and titles for matching—avoid sending sensitive unpublished material you don't want transmitted. If privacy is a concern, run the script locally in an isolated environment, inspect the full scripts/main.py (especially any network call implementations) before running, and consider auditing network traffic or substituting only the APIs you trust. If you need offline-only checks, verify the code supports a local database/fallback path before using.Like a lobster shell, security has layers — review code before you run it.
latestvk971fytvs8t2tndp7fkpvhaa4n83zqc0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.