Deals ToMe

v1.0.1

Curates three trusted daily deals showing best savings, trending offers, and personalized picks from top public deal sites.

0· 48·0 current·0 all-time
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, description, listed sources, and outputs align: the skill claims to curate three daily deals from public deal sites and the SKILL.md enumerates those sites and fixed output fields. No unexpected credentials, binaries, or installs are requested.
Instruction Scope
SKILL.md restricts behavior (read_only, public_only, respect_robots, no_login, no_form_submit) and specifies exact sources and output structure. One minor note: the 'For You' personalized slot implies using user-provided preferences or conversation context for matching; the document does not instruct the agent to read local files or other secrets, but ensure personalization does not cause the agent to request or transmit sensitive personal data.
Install Mechanism
No install spec and no code files — instruction-only means nothing is written to disk or downloaded during installation.
Credentials
No environment variables, credentials, or config paths are requested; this is proportionate for a read-only aggregator of public deal sites.
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges. Autonomous invocation is allowed by default but not combined with other risky factors here.
Assessment
This skill appears to do what it says: aggregate three public deals from well-known deal sites and requires no credentials or installs. Before enabling, consider: (1) the skill will likely use your conversation context to produce the 'For You' pick — avoid sharing sensitive personal data when asking for personalization; (2) scraping public sites can still run into site rate limits or ToS — expect occasional missing results or the need to respect robots; and (3) because it is an instruction-only skill there is no hidden code, but also no packaged validation — monitor outputs and decline if results look suspicious.

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

latestvk975g9f1mzq5q31v1v7n0jdw0983zg2d

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments