competition-web-runtime

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and process untrusted data from external web sources.\n
  • Ingestion points: The skill instructs the agent to analyze untrusted artifacts including Entry HTML, boot scripts, runtime configuration, and API responses (documented in SKILL.md and references/routing-runtime.md).\n
  • Boundary markers: The instructions lack specific delimiters or warnings to treat text embedded within the analyzed data as non-instructional content.\n
  • Capability inventory: The skill facilitates the capture and analysis of network requests, headers, and browser storage, which are sensitive operations when performed on untrusted input.\n
  • Sanitization: There are no instructions for sanitizing or escaping the external content before it is processed by the agent.\n- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration files; no executable scripts, binaries, or library dependencies are included in the package.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 12:15 PM