Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
- The skill documentation and usage clearly indicate access to environment variables (API key), network operations (web scraping/search/crawl), and file writes (screenshots/output docs), yet no permissions are explicitly declared. This creates a transparency and policy-enforcement gap: an agent or reviewer may authorize the skill without understanding its actual capabilities, increasing the risk of unintended external requests or local file modification.
