letterboxd-watchlist
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill makes network requests to letterboxd.com, a well-known film social media service, to fetch public watchlist data. This operation is performed using standard libraries (urllib.request) and targets the service's official domain, posing no risk of unauthorized data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the web, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: scripts/scrape_watchlist.py reads HTML content from Letterboxd.
- Boundary markers: Data is extracted via regex and written to CSV or JSONL files. No specific delimiters are used to warn downstream consumers about the nature of the content.
- Capability inventory: The skill has the ability to write to local files but does not execute commands or scripts based on the ingested content.
- Sanitization: Basic sanitization is performed via HTML unescaping and standard JSON serialization.
Audit Metadata