frontend-docs-context7

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves and processes external documentation for various frontend libraries, creating a potential surface for indirect prompt injection where malicious content in third-party docs could influence agent behavior. \n- Ingestion points: External documentation content is ingested using the mcp_io_github_ups_get-library-docs tool as defined in SKILL.md. \n- Boundary markers: The skill lacks explicit instructions or markers to distinguish between documentation content and system instructions. \n- Capability inventory: The skill is primarily focused on information retrieval and providing code examples, which limits the potential impact of an injection. \n- Sanitization: No sanitization or validation of the fetched documentation content is described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:22 AM