write-gitbook

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill contains instructions for the AI agent to perform network requests to https://gitbook.com/docs/skill.md?ask=<question> to retrieve additional documentation context. This is directed to the official domain of the vendor (gitbookio) and serves the primary purpose of the skill.
  • [DATA_EXFILTRATION]: User-provided questions are transmitted to the gitbook.com domain as query parameters. This behavior is documented as a feature for querying the vendor's documentation database.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface where the agent is instructed to fetch and process content from a remote URL.
  • Ingestion points: The Agent Instructions section in SKILL.md defines the retrieval mechanism.
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: The agent is instructed to use HTTP GET capabilities to fetch remote content.
  • Sanitization: There are no instructions provided for sanitizing or validating the content returned from the external documentation source.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 01:15 PM
Security Audit — agent-trust-hub — write-gitbook