fetch-api-reference

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches latest API reference documentation from the official developer documentation site.
  • [SAFE]: Correctly identifies that API secrets should be managed as placeholders rather than hardcoded credentials.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by instructing the agent to treat remote web content as an authoritative source of truth.
  • Ingestion points: Fetches remote content from the RunwayML documentation URL specified in SKILL.md.
  • Boundary markers: Absent; external content is explicitly instructed to take precedence over existing skill documentation.
  • Capability inventory: The agent uses the retrieved data to guide integrations involving API requests and data handling.
  • Sanitization: No validation or sanitization logic is provided for the fetched documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 12:14 AM