find-skills

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by instructing the agent to interpolate untrusted user search queries directly into shell command arguments.
  • Ingestion points: User-provided queries in the 'Search for Skills' section of SKILL.md.
  • Boundary markers: Absent. There are no delimiters or instructions to ignore embedded commands within the user's query.
  • Capability inventory: Shell command execution via 'npx skills' as documented in SKILL.md.
  • Sanitization: Absent. There is no logic provided to escape or validate user-supplied query strings before execution.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands ('npx skills find' and 'npx skills add') to interact with an external package ecosystem. It specifically recommends using the '-y' flag for installation, which bypasses user confirmation prompts and could lead to the silent installation of malicious packages if the agent is misled by search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:22 PM
Security Audit — agent-trust-hub — find-skills