Skills
Navigate
skills/hkuds/cli-anything/cli-anything-exa/Gen Agent Trust Hub

cli-anything-exa

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the web through its search and contents commands. This creates a surface for indirect prompt injection where malicious instructions embedded in web pages could influence the agent's behavior.
  • Ingestion points: The search and contents subcommands in SKILL.md are designed to bring external web data into the agent's context.
  • Boundary markers: The instructions do not define specific delimiters or warnings to treat search results as untrusted data.
  • Capability inventory: The skill is primarily focused on search and content retrieval; however, the agent's overall capabilities (such as command execution) determine the potential impact.
  • Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned in the skill definition.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include a command to install the CLI directly from a GitHub repository hosted by the vendor.
  • Evidence: pip install git+https://github.com/HKUDS/CLI-Anything.git#subdirectory=exa/agent-harness in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:21 PM
Security Audit — agent-trust-hub — cli-anything-exa