weather-svg-creator

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it interpolates untrusted external data (temperature, city name) directly into generated file content.
  • Ingestion points: The calling agent provides temperature values and city names which are inserted into the SVG and Markdown templates (SKILL.md).
  • Boundary markers: Absent; there are no instructions for the agent to treat this data as untrusted or to ignore instructions embedded within the data.
  • Capability inventory: The skill allows writing files to the local filesystem in the orchestration-workflow/ directory (SKILL.md).
  • Sanitization: Absent; the skill does not require escaping or validating the input data, potentially allowing for the injection of malicious SVG tags or Markdown content.
  • [NO_CODE]: The skill logic is entirely defined within natural language instructions and does not include any external script files, binaries, or source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 03:35 AM
Security Audit — agent-trust-hub — weather-svg-creator