ClawHub

Shopify Influencer Campaign

v1.0.0

Plan and execute influencer marketing campaigns for Shopify stores including outreach, briefs, and ROI tracking. Triggers: influencer campaign, influencer ma...

⭐ 0· 131·0 current·0 all-time
by@mguozhen
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description match the included materials: SKILL.md and analyze.sh are focused on generating influencer campaign strategies, templates, and measurement guidance. There are no unrelated environment variables, binaries, or config paths requested.
✓
Instruction Scope
SKILL.md gives narrowly scoped instructions (campaign planning, outreach templates, tracking). The included analyze.sh builds a prompt and invokes a local agent to produce the campaign; it does not instruct reading arbitrary files, exfiltrating data, or contacting external endpoints itself.
✓
Install Mechanism
No install spec is present (instruction-only plus a small helper script). Nothing is downloaded or written to disk by an installer; risk from installation is low.
✓
Credentials
The skill declares no required environment variables or credentials. The helper script uses only harmless local data (timestamp and the user's input) and expects a local openclaw CLI binary; no secret access is requested.
✓
Persistence & Privilege
always is false and the skill does not request or modify other skills or system-wide configuration. It does not request persistent presence or elevated privileges.
Assessment
This skill appears coherent and limited to generating influencer campaign content. Before running analyze.sh, review it (it simply builds a prompt and calls the local `openclaw agent` CLI). Ensure you trust the local openclaw binary and avoid pasting sensitive credentials or private store tokens into the prompt. If you want extra assurance, run the script in a sandboxed environment or paste the PROMPT into a trusted agent manually rather than executing the script directly.

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

latestvk97935khkr61dccgkkrew2w0pn83nhe0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments