Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Open Access Scout

v1.0.0

Use when finding open access journals, checking journal policies, or identifying predatory publishers. Helps researchers locate legitimate open access venues...

0· 36·0 current·0 all-time
byAIpoch@aipoch-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The skill description and SKILL.md emphasize finding OA journals, checking journal policies, assessing predatory publishers, APC comparison, and indexed-status checks. The only packaged code (scripts/main.py) implements a tiny OpenAccessScout that mock-returns OA copies of individual papers and lists a handful of sources. There is no implementation of journal-level searches, APC comparisons, indexing checks, or predatory publisher heuristics. Example usage in SKILL.md references different module/file names (scripts/oa_scout, scripts/oa_scout.py) that do not exist, increasing the mismatch.
Instruction Scope
SKILL.md primarily instructs running the packaged script and following a bounded workflow, which is appropriate. However several concrete examples and Quick Start snippets reference non-existent files/modules and CLI names (oa_scout vs main.py), which may mislead users. The instructions do not ask for unrelated files, credentials, or system paths.
Install Mechanism
No install spec and no external downloads are included; this is an instruction-only skill with a small bundled script. That minimizes install risk.
Credentials
The skill requests no environment variables, no credentials, and no config paths. The code does not access environment secrets. (Note: SOURCES includes 'Sci-Hub (use with caution)', which is a legal/ethical flag but not a credential request.)
Persistence & Privilege
always is false, the skill is user-invocable and can be called autonomously (platform default). The skill does not request persistent system presence or alter other skills/configs.
What to consider before installing
This package is inconsistent: the SKILL.md promises journal-level features (predatory checks, APC comparisons, indexing filters) but the included script only mock-searches for open-access copies of individual papers. Before installing or granting this skill to an agent: 1) decide whether you need a journal/publisher scout or a paper-level OA finder — this package appears to be the latter. 2) Inspect scripts/main.py yourself (it contains no network calls and is small), and run the recommended checks: python -m py_compile scripts/main.py and python scripts/main.py --help to confirm behaviour. 3) Don't rely on the SKILL.md examples that reference scripts/oa_scout.py or modules that aren't present; ask the author for a corrected release if you expected APC or predatory-publisher functionality. 4) Note the SKILL.md mention of Sci-Hub: that is a legal/ethical caution (not malicious code), so avoid instructing agents to retrieve paywalled content from illegal sources. If you require the promised journal-level features, treat this package as incomplete or mislabeled and do not use it as-is.

Like a lobster shell, security has layers — review code before you run it.

latestvk97a27thc1d1t66597x1ekb3nn83xwgz

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments