skills/sonvee/ai-skills/find-skills/Gen Agent Trust Hub

find-skills

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading and installing external agent capabilities from the skills.sh registry and GitHub repositories (such as vercel-labs/agent-skills) using the npx skills add command. These downloads originate from well-known or trusted sources and are essential to the skill's documented purpose.- [COMMAND_EXECUTION]: The skill is designed to execute shell commands via the npx utility to manage the lifecycle of agent skills. This includes searching (find), installing (add), checking for updates (check), and updating (update) packages.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by ingesting and processing search results from an external registry.
  • Ingestion points: Results from the npx skills find [query] command in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the search result processing instructions.
  • Capability inventory: The skill can execute subprocesses via npx and modify the environment by installing new tools.
  • Sanitization: No specific sanitization or validation of the registry output is performed, though the instructions guide the agent to present options to the user for manual approval before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:53 PM