Skill flagged — suspicious patterns detected

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

Grammar Checker Ama

v0.1.0

Grammar checking tool for AMA style medical writing

0· 84·0 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 claim features like 'AMA style compliance' and 'medical terminology validation', but the included script (scripts/main.py) only implements a very small passive‑voice check using a hardcoded list of phrases. This is a capability mismatch: the advertised functionality is not present in the code.
Instruction Scope
SKILL.md instructs running `python scripts/main.py --text "..."`, which matches the script's CLI. However the documentation refers to reading/writing input/output files and various risk mitigations (input validation, sandboxing) that the script does not implement. The instructions are broader and more security‑conscious than the actual runtime behavior; they leave important validation and file‑IO protections to the environment rather than implementing them.
Install Mechanism
No install spec is provided (instruction-only with a small Python script). This is low risk from an installation perspective because nothing is downloaded or installed automatically.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The script reads only CLI input and prints output to stdout. The requested environment access is minimal and proportional to the apparent runtime behavior.
Persistence & Privilege
The skill is not always-enabled and does not request any persistent privileges or modify other skills or system configuration. It runs only when invoked by the user/agent.
What to consider before installing
This skill's code is small and readable but does not implement most features claimed in the documentation (AMA compliance, medical terminology checks). If you consider installing/use: 1) Treat the tool as very limited — it only looks for a few hardcoded passive‑voice phrases. Do not rely on it for clinical or publication decisions. 2) Ask the author for provenance, tests, and a changelog (no homepage or publisher metadata is provided). 3) Require unit tests or representative sample inputs/outputs to verify the advertised features before using in production. 4) Run the script in a sandboxed environment and review any changes if you extend it to read/write files. 5) If you need real AMA/style checks or terminology validation, prefer a well‑maintained tool or service with documented algorithms and tests.

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

latestvk97b3ecvvzfnjx04yjqsjpsvj183esf2

License

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

Comments