skills-sh-search

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches metadata and repository content from the skills.sh website and GitHub to enable browsing and installation of agent extensions.
  • [COMMAND_EXECUTION]: Executes shell commands using the npx skills CLI tool to search the directory and manage local skill installations.
  • [PROMPT_INJECTION]: Exhibits an indirect prompt injection surface because it processes untrusted Markdown content (SKILL.md) from third-party GitHub repositories.
  • Ingestion points: Remote content fetched via WebFetch and CLI search results in SKILL.md.
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the fetched skill descriptions.
  • Capability inventory: Includes shell command execution (npx) and file system writes during installation.
  • Sanitization: No automated filtering or sanitization of the fetched external markdown is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:18 PM
Security Audit — agent-trust-hub — skills-sh-search