Skills
skills/halo-dev/cli/halo-cli-search/Gen Agent Trust Hub

halo-cli-search

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the halo CLI binary for searching content on Halo sites. The commands provided in SKILL.md are standard search operations using keywords and site URLs.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes data from external websites. * Ingestion points: External content fetched via halo search command in SKILL.md. * Boundary markers: No delimiters or warnings used to separate external content from instructions. * Capability inventory: Focuses on data retrieval and outputting search results. * Sanitization: No evidence of data sanitization before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:45 AM