user-activation-contracts

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes user-provided technical scenarios and failure logs regarding browser API behaviors. This processing of untrusted external content represents a surface for indirect prompt injection.\n
  • Ingestion points: User descriptions of code execution sequences and browser interaction logs provided during analysis.\n
  • Boundary markers: The instructions do not define specific delimiters or directives to ignore instructions embedded within the analyzed data.\n
  • Capability inventory: The skill is primarily instructional and diagnostic; it does not explicitly define tools for file system access, network exfiltration, or command execution.\n
  • Sanitization: No explicit sanitization or validation of the ingested input data is described.\n- [EXTERNAL_DOWNLOADS]: The skill references official documentation and technical issue trackers from established sources including Mozilla, WHATWG, and GitHub. These links are provided for educational and technical reference purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:59 PM
Security Audit — agent-trust-hub — user-activation-contracts