guarded-websearch-codex

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONOBFUSCATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Bash script quarantine-search-codex.sh to execute the codex CLI with search capabilities. The execution is performed within a restricted environment using --sandbox read-only and --ephemeral flags to prevent persistent changes or unauthorized file system access. The script includes input validation to block shell metacharacters like backticks or subshell expansion in the search query.
  • [OBFUSCATION]: The sanitize.ts script includes logic to detect and remove zero-width characters, bidirectional overrides, and other invisible Unicode characters from search results. This is a security feature designed to prevent 'invisible character' prompt injection attacks where malicious instructions are hidden in plain sight.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed specifically to mitigate indirect prompt injection vulnerabilities. It ingests untrusted data from web search results (titles and snippets) and passes them through a static sanitizer (sanitize.ts) that filters for known attack patterns like instruction overrides ('ignore previous instructions') and chat template markers. It provides mandatory boundary reporting via aggregate_flags so the main agent can assess the safety of the results.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 02:36 AM