Campaign Performance Report
v1.0.0Multi-channel marketing performance agent. Pulls together Meta, Google, email, and organic data into a unified weekly report with AI executive commentary — e...
⭐ 0· 88·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (multi-channel report) aligns with the instructions: it accepts pasted numbers/CSV uploads, normalizes metrics, analyzes trends, and saves reports. There are no unrelated environment variables, binaries, or external integrations requested that would be inconsistent with reporting functionality.
Instruction Scope
SKILL.md confines runtime behavior to accepting manual inputs/CSV data, normalizing metrics, producing analyses, and saving reports to a local workspace. It does not instruct reading arbitrary system files, contacting external endpoints, or accessing credentials. It does permit the agent to create files in the user's home directory (~/campaign-reports/), which is coherent with the stated workspace behavior.
Install Mechanism
No install spec or code is present (instruction-only). Nothing is downloaded or written by an installer, so there is low install risk.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That matches its stated manual/CSV workflow — no disproportionate credential access is requested.
Persistence & Privilege
The skill persists data to ~/campaign-reports/ (memory.md, reports/, data/). This is expected for a reporting tool, but users should be aware that account KPIs or exported CSVs (which may contain sensitive info) will be stored persistently in their home directory.
Assessment
This skill appears coherent and does not request credentials or installs, but it will store uploaded CSVs and derived data under ~/campaign-reports/ (memory.md, reports/, data/). Before using: (1) avoid pasting API keys, passwords, or other secrets into the agent; (2) inspect and, if needed, delete ~/campaign-reports/ after use or run the skill in an isolated account/environment; (3) review the referenced GitHub homepage to confirm provenance and check for any published code or instructions you may want to vet; (4) be mindful that allowed-tools: Bash means the agent can create and modify files locally — that matches the skill’s purpose but is worth noting if you have stricter filesystem policies.Like a lobster shell, security has layers — review code before you run it.
latestvk97cjra9eag65apwg4z54mpzb5838x5t
License
MIT-0
Free to use, modify, and redistribute. No attribution required.