skills/tkersey/dotfiles/seq/Gen Agent Trust Hub

seq

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The SKILL.md file contains a run_seq function that automates the installation of the seq CLI using brew install tkersey/tap/seq, fetching the binary from the author's Homebrew tap.
  • [COMMAND_EXECUTION]: The skill executes various shell commands including OS identification via uname and execution of the seq binary with arguments and JSON query specifications.
  • [INDIRECT_PROMPT_INJECTION]: The tool is designed to ingest and analyze agent session JSONL files and markdown memories, which may contain malicious instructions from previous untrusted interactions. * Ingestion points: ~/.codex/sessions and ~/.codex/memories. * Boundary markers: No specific delimiters or warnings for processed content are mentioned. * Capability inventory: The skill has shell execution capabilities via the run_seq wrapper. * Sanitization: The instructions do not define sanitization procedures for the mined data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:42 AM