Sanfrancisco Today Festivalevents Agent

Harvests, indexes, and searches today's festivals and events in San Francisco.

Security Scan

The skill's code, runtime instructions, and requirements match its stated purpose of scraping today's SF events and storing/searching them in a local ChromaDB; nothing requests unrelated credentials or external installs beyond normal Python packages.

Purpose & Capability

The name/description claim scraping, indexing, and searching today's SF events. The included Python script targets https://sf.funcheap.com/today/, extracts event metadata, and integrates with a local ChromaDB collection — all consistent with the stated purpose. No unrelated services or credentials are requested.

Instruction Scope

SKILL.md instructs the agent to run the provided script with specific actions (list, ingest, search, json). The script performs HTTP GET requests to a single known site, parses the HTML, prints results, and writes/query a local ChromaDB at ./rag_db. It does not read arbitrary system files, access unrelated env vars, or post data to external endpoints beyond the target scrape site.

Install Mechanism

No automated install spec is included (instruction-only), which lowers risk. README suggests installing Python dependencies (requests, beautifulsoup4, chromadb) via pip — this is proportional. Note: the skill will create persistent data under ./rag_db when using ChromaDB; there is no external binary download or archive extraction in the package.

Credentials

The skill declares no required environment variables or credentials and the code does not attempt to read secrets. All resource access (network to the scrape target and local ./rag_db) is appropriate for a web-harvesting and local-RAG skill.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system-wide config. It persists harvested data locally in ./rag_db via ChromaDB, which is expected behavior for an indexing agent and is within its stated scope.

Assessment

This skill appears coherent with its description. Before installing: (1) review and install the Python dependencies in a virtual environment (requests, beautifulsoup4, chromadb); (2) be aware the agent will write a local vector DB at ./rag_db (delete or sandbox that directory if you have privacy concerns); (3) the script performs live HTTP requests to sf.funcheap.com — ensure that scraping that site complies with its terms of service and your network policy; (4) inspect the included script yourself if you want to confirm there are no hidden endpoints or changes; (5) run it in a restricted environment or container if you prefer to limit filesystem/network access. No credentials are requested and nothing in the package appears to exfiltrate data to unexpected remote hosts.

San Francisco Today Events Harvester

This skill provides the ability to scrape live event data from SF Funcheap and interact with a local RAG database (ChromaDB) to find specific activities.

Agent Instructions

When the user asks about events in San Francisco today:

1. Use the script SanFrancisco-Today-FestivalEvents-Harvester-Agent.py.
2. To see live listings, run: python3 SanFrancisco-Today-FestivalEvents-Harvester-Agent.py --action list --scope top
3. To search previous harvests, run: python3 SanFrancisco-Today-FestivalEvents-Harvester-Agent.py --action search --query "<user query>"
4. To update the local database with full listings, run: python3 SanFrancisco-Today-FestivalEvents-Harvester-Agent.py --action ingest --scope full