Info Magnet
v1.0.0Info Magnet — set up topics you care about and let information come to you. Supports web search, RSS feeds, and URL monitoring. Periodic scans push relevant...
⭐ 0· 35·0 current·0 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 (monitoring web/RSS/URLs, periodic scans, digests) align with the included SKILL.md and the Python script. Required binaries are only python and no credentials or unrelated binaries are requested.
Instruction Scope
Runtime instructions are scoped to creating/listing/managing magnets, fetching RSS, simple webpage checks, and producing digests. The agent is expected to perform web_search for web-result enrichment; this is explicitly documented. The skill stores state under ~/.openclaw/memory which is consistent with its purpose. It does not instruct the agent to read unrelated system files or secrets.
Install Mechanism
No install spec (instruction-only with a shipped Python script). No downloads or external installers are invoked. This is the lowest-risk install pattern for this functionality.
Credentials
No environment variables, API keys, or credentials are requested. The skill only needs outbound HTTP access to fetch RSS/web pages and relies on agent-provided web_search for searches; that is proportionate to the stated capabilities.
Persistence & Privilege
always: false and model-invocation is allowed (platform default). The skill writes its own data under ~/.openclaw/memory (magnets.json, magnet-seen.jsonl, magnet-digests/) which is expected. It does not attempt to modify other skills or system-wide agent settings.
Assessment
This skill appears to do what it says: it will make outbound HTTP requests to RSS feeds, URLs you configure, and expects the agent to run web_search for web lookups. Before enabling: (1) review the full infomagnet.py (it’s included) if you need to confirm exact behavior; (2) avoid adding magnets that point to private/internal URLs or to feeds containing sensitive tokens, since the skill will fetch those addresses; (3) if you run agents in sensitive environments, consider restricting network access or running the skill in a sandbox; (4) integrating the skill with your HEARTBEAT or message channel will cause it to run periodically — ensure you’re comfortable with that cadence and stored summaries under ~/.openclaw/memory.Like a lobster shell, security has layers — review code before you run it.
latestvk97cs5tedsr2khcm97r6sax76d843d1b
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binspython