Skills
skills/duc01226/easyplatform/research/Gen Agent Trust Hub

research

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the gemini CLI tool via bash to perform technical searches.
  • [EXTERNAL_DOWNLOADS]: Fetches data from external sources using the gemini CLI, WebSearch tool, and the docs-seeker skill for GitHub repository analysis.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted data from the web. 1. Ingestion points: External content retrieved from web searches, GitHub repositories, and CLI tool outputs (SKILL.md). 2. Boundary markers: Absent. The skill does not specify delimiters or instructions to ignore potential commands within the researched material. 3. Capability inventory: Includes task creation (TaskCreate), file writing (report saving), and shell command execution (gemini CLI). 4. Sanitization: Absent. There are no instructions for sanitizing or validating the content retrieved from external sources before it is used for analysis and reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — research