Promote
v0.3.0Helps plan and draft tailored promotional content for your project across multiple platforms, ensuring context fit and staggered publishing for best reach.
⭐ 0· 92·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description (promote across platforms) align with the SKILL.md which provides platform-specific drafting and publishing guidance. However, the skill does not declare any required credentials or integrations even though real publishing normally requires API keys or account access; this is an omission rather than a direct mismatch.
Instruction Scope
The instructions stay on-topic (ask for context, create platform-tailored drafts, use draft/publishing flags, stagger posts). They do not direct reading unrelated files, accessing system paths, or exfiltrating data. They assume 'tools for publishing' exist but don't instruct broad data collection.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk installation footprint — nothing will be written to disk by the skill itself.
Credentials
The skill declares no environment variables or credentials. That's safer in principle, but practically incomplete: publishing requires platform credentials (API tokens, OAuth). The skill should document what integrations or tokens are expected so you can judge whether to provide them and with what scope.
Persistence & Privilege
always:false and default autonomous invocation behavior are normal. The skill does not request permanent presence or claim to modify other skills or global agent configuration.
Assessment
This skill appears coherent and low-risk as written, but before enabling it consider: 1) Which publishing tools or account tokens does your agent already have? The skill doesn't declare credentials, yet posting requires API keys or OAuth — verify and limit their scope. 2) Prefer requiring user approval before any live publishes (the SKILL.md suggests drafts; enforce that). 3) Never grant full account credentials; use limited tokens and review token scopes and rotation policies. 4) Review generated drafts for accidental disclosure of secrets or proprietary details before publishing. 5) If you need the agent to actually post, ask the skill author to document required integrations and failure modes so you can audit them.Like a lobster shell, security has layers — review code before you run it.
latestvk976vf3bs9mf25zb5e5r19jn4s83azam
License
MIT-0
Free to use, modify, and redistribute. No attribution required.