Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/notion-cost-tuning/Gen Agent Trust Hub

notion-cost-tuning

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions recommend installing several well-known and trusted Node.js packages from the npm registry.\n
  • The packages include @notionhq/client, p-queue, lru-cache, node-cache, and express.\n- [COMMAND_EXECUTION]: The skill provides standard npm install commands for managing the necessary project dependencies.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data ingested from the Notion API, which establishes a surface for indirect prompt injection if the source content contains malicious instructions.\n
  • Ingestion points: Data enters the agent context through notion.databases.query and notion.pages.retrieve calls in references/implementation.md.\n
  • Boundary markers: The implementation examples do not use explicit delimiters or instructions to ignore embedded content for the data retrieved from Notion.\n
  • Capability inventory: The skill is configured with Write, Edit, and Bash tool access as defined in the SKILL.md frontmatter.\n
  • Sanitization: The provided code focuses on API request efficiency and does not demonstrate specific sanitization or filtering of the text content returned by the Notion API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 01:47 PM