Social Content Generator
v1.0.0Generate social media content (posts, captions, images) for multiple platforms. Use when creating social media posts, marketing content, or bulk content cale...
⭐ 0· 221·1 current·1 all-time
byYinanping@yinanping-cpu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match the included generate_post.py (AI text + optional image generation). However SKILL.md describes additional scripts (generate_calendar.py, upload_post.py) and platform-upload capabilities that are not present in the file manifest, which is inconsistent with the claimed multi-script capability.
Instruction Scope
SKILL.md instructs use of .env variables (OPENAI_API_KEY and platform API tokens) and references calendar and upload scripts. The only runnable file is generate_post.py which does use OpenAI and may call out to download images, but the manifest and registry declare no required env vars. The instructions thus ask the agent/user to provide credentials that the skill metadata doesn't declare, and they reference files that are missing.
Install Mechanism
This is an instruction-only skill with a single Python script (no install spec). The script imports third-party packages (openai, requests) but the package/dependency list is not declared. That omission is a distribution/maintenance risk (users may run it without required libs). No remote download URLs or obfuscated installers are present.
Credentials
SKILL.md expects sensitive API credentials (OPENAI_API_KEY, Twitter/Instagram/LinkedIn tokens) but the skill metadata declares no required environment variables or primary credential. Requesting or instructing use of multiple platform tokens is plausible for an uploader, but because upload functionality is only described (not included) and the manifest doesn't declare credential needs, the credential scope and disclosure are under-specified and inconsistent.
Persistence & Privilege
always is false and the skill does not request system-wide changes or persistent/automatic installation. It does not attempt to modify other skills' configs. Default autonomous invocation is allowed (normal) and not combined with other high-risk flags.
What to consider before installing
This skill appears to be a legitimate social-post generator, but there are several red flags you should address before using it:
- Missing files: SKILL.md references generate_calendar.py and upload_post.py but only generate_post.py is included. Ask the author for the missing scripts or remove references if they're not part of the package.
- Undeclared credentials: The README/skill suggests you must provide OPENAI_API_KEY and platform tokens, yet the registry metadata lists no required env vars. Treat API keys as sensitive—only provide them after confirming exactly which script needs them and why.
- Undeclared dependencies: The script uses the openai and requests Python packages but the skill provides no install/dependency spec. Install dependencies in a virtualenv and inspect the code before running.
- Network behavior: generate_post.py will call OpenAI and download images from URLs returned by the API. This is expected for image/text generation, but be aware that your prompt/topic content and any generated content will be sent to OpenAI. Use limited-scope API keys and quotas.
- Safety steps: run the script in an isolated environment (container or VM), avoid hardcoding tokens or committing .env to repos, restrict API key scopes where possible, and ask the publisher to provide: (1) complete file set, (2) a requirements.txt or install instructions, and (3) explicit documentation for which env vars are actually needed. If the uploader feature is required, request the upload_post.py source for review before providing platform credentials.
If you want, I can (a) inspect any missing scripts you obtain, (b) produce a safe requirements.txt and minimal run instructions, or (c) point out exact lines where environment variables are referenced inside the code.Like a lobster shell, security has layers — review code before you run it.
latestvk97ejxabd2q9fp967hxhgapkm182e86p
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
