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

seq

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches source code from the author's GitHub repository (github.com/tkersey/skills-zig) and utilizes a Homebrew tap (tkersey/tap/seq) for tool installation.\n- [COMMAND_EXECUTION]: Executes shell commands to build and install the 'seq' CLI tool, including 'zig build' for compilation and 'install' for binary placement.\n- [PROMPT_INJECTION]: Susceptible to indirect prompt injection via processed session data (Category 8).\n
  • Ingestion points: Mines JSONL session logs from ~/.codex/sessions, markdown memories from ~/.codex/memories, and Opencode history from ~/.local/share/opencode/opencode.db.\n
  • Boundary markers: Absent; the skill does not use specific delimiters or warnings to isolate log content from instructions.\n
  • Capability inventory: Performs local command execution via the 'seq' tool and accesses various database and memory files.\n
  • Sanitization: No evidence of content sanitization or filtering is present for the data read from session artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:36 AM