MoA Explainer
v1.0.0Generate 3D animation scripts and lay explanations for drug mechanisms.
⭐ 0· 56·0 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/description (MoA animation scripts and lay explanations) matches the packaged artifact (scripts/main.py) and SKILL.md. The Python script produces storyboards and simplified explanations and requires only local inputs; no unrelated credentials, binaries, or cloud access are requested.
Instruction Scope
SKILL.md instructs the agent/user to validate inputs and run scripts/main.py and the script itself only reads CLI args and writes output files or prints results. There are a couple of minor inconsistencies to be aware of: (1) SKILL.md references an in-file CONFIG block and additional prereqs that do not exist in the repository, and (2) the script writes to whatever path is passed via --output without validating or sanitizing the path (no protection against accidental/intentional directory traversal or overwriting files). Functionally this stays inside the declared purpose, but input/output path handling and some prompt text (mechanism.split()[0]) are fragile and should be reviewed.
Install Mechanism
There is no install spec and the skill is instruction-only with a small, self-contained Python script using only the standard library. This minimizes installation risk (nothing is downloaded or executed from an external URL).
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportionate for a local content-generation script.
Persistence & Privilege
The skill is not set to always: true and does not request to modify other skills or system-wide settings. It runs only when invoked and writes output only to the user-specified output file.
Assessment
This skill appears to do what it says: locally generate animation scripts and simplified explanations. Before installing or running it: (1) Review and test the script in a sandbox or isolated workspace; it will write the text to any --output path you supply and does not validate that path, so avoid passing sensitive filesystem locations and beware of accidental overwrites. (2) Verify the generated medical content for accuracy and suitability for your audience—this tool is a content generator and not a medical authority. (3) Note some minor repository inconsistencies (a referenced CONFIG block and prereqs that are not present); those are quality issues rather than active threats but you should inspect the source if you plan to automate runs. (4) Because the publisher/homepage are unknown, prefer local/manual invocation rather than granting persistent/autonomous privileges in an agent until you are comfortable with the provenance. If you need stronger safety guarantees, add path validation and explicit input sanitization, and run the script in a restricted environment.Like a lobster shell, security has layers — review code before you run it.
latestvk97bv6wyek8gd0aa05z2t1k03583qakd
License
MIT-0
Free to use, modify, and redistribute. No attribution required.