San Francisco
v1.1.0Navigate San Francisco as visitor, resident, tech worker, student, or entrepreneur with neighborhoods, transport, costs, safety, and local insights.
⭐ 2· 448·2 current·2 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Skill name/description match the included files (neighborhoods, transport, costs, safety, startup/tech guidance). No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to load and serve the included topical files and to provide 'practical guidance with current data.' The runtime instructions do not direct the agent to read system files, access credentials, or transmit data externally. The only minor ambiguity: 'current data' is asserted but there is no install or connector described to refresh live data (this affects accuracy, not security).
Install Mechanism
No install spec and no code files to execute; instruction-only skills are lowest-risk for disk/network installs. Nothing will be downloaded or written as part of an installer.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. There is no disproportionate request for secrets or external service access.
Persistence & Privilege
always is false (default). The skill does not request persistent elevated privileges or to modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not combined with other red flags.
Scan Findings in Context
[no_findings] expected: This is an instruction-only skill composed of markdown files; the regex scanner had no code to analyze. Absence of findings is expected but does not guarantee correctness of the content.
Assessment
This skill appears coherent and low-risk: it is a local content bundle (tips, neighborhood/transport/costs) and asks for no credentials or installs. Before relying on it: 1) remember the 'current data' claim is vague — verify time-sensitive facts (rent, transit fares, salaries) against live sources; 2) the skill owner is unknown, so prefer non-sensitive queries (travel, neighborhood advice) rather than sharing personal or account information through the skill; 3) ask the agent to cite sources or dates when it gives numeric or 'current' figures; and 4) if you need live/authoritative data, pair this skill with an official API or site rather than trusting it as a single source.Like a lobster shell, security has layers — review code before you run it.
latestvk975g82sse423bt6smrjfzxpqh81c7gc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🌉 Clawdis
OSLinux · macOS · Windows