tech-radar-context

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches technology radar data from https://tikalk.com/radar.json via the provided helper scripts. This URL belongs to the skill's author domain and is used to retrieve the dataset necessary for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes and injects content from an external web resource into the agent context, creating a potential surface for indirect prompt injection if the remote source were compromised.
  • Ingestion points: scripts/radar-search.sh and scripts/radar-search.ps1 ingest data from https://tikalk.com/radar.json.
  • Boundary markers: The skill outputs the results within a structured Markdown table titled 'Tikal Tech Radar Context'.
  • Capability inventory: The skill uses curl, jq, and Invoke-RestMethod to retrieve and parse data, but it does not execute the data as code.
  • Sanitization: The processing scripts include logic to strip HTML tags (using <[^>]+> patterns) and truncate the text to 160 characters before it is presented to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:01 PM
Security Audit — agent-trust-hub — tech-radar-context