fsa-announcements
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests announcement data from official external web sources (www.fsa.go.jp). While this creates an ingestion surface common to news-gathering skills, the risk is minimized by the skill's restricted capabilities. Ingestion points: scripts/fetch_announcements.py fetches data from RSS and HTML endpoints. Boundary markers: Data is returned in a structured JSON format without specific delimiters. Capability inventory: Limited to network access and optional, user-controlled filesystem caching. Sanitization: Uses html.unescape and regex for structural extraction.
- [REMOTE_CODE_EXECUTION]: The skill implements robust security by strictly validating that all fetched URLs use the 'http' or 'https' schemes, preventing attacks via other protocols. By relying exclusively on the Python standard library, it eliminates supply-chain risks associated with third-party packages.
Audit Metadata