app-discovery-scrutiny

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (scripts/score.py) to process and weight app candidate data. The script is used for mathematical scoring and does not perform dangerous system operations or file modifications.
  • [EXTERNAL_DOWNLOADS]: The framework instructs the agent to use web search tools to gather real-world market data and competitor information, which is consistent with its stated purpose of professional research.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided app descriptions. While this creates a standard indirect prompt injection surface common to AI agents, the instructions use clear structure to mitigate accidental obedience to embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:39 AM
Security Audit — agent-trust-hub — app-discovery-scrutiny