ia-file-todos — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ia-file-todos (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
{issue_id}-{status}-{priority}-{description}.mdpending (needs triage), ready (approved), complete (done)p1 (critical), p2 (important), p3 (nice-to-have)Examples: 001-pending-p1-mailer-test.md, 002-ready-p1-fix-n-plus-1.md, 005-complete-p2-refactor-csv.md
Use todo-template.md as a starting point. YAML frontmatter:
---
status: ready # pending | ready | complete
priority: p1 # p1 | p2 | p3
issue_id: "002"
tags: [typescript, performance, database]
dependencies: ["001"] # Issue IDs this is blocked by
---Required sections: Problem Statement, Findings, Proposed Solutions, Recommended Action, Acceptance Criteria, Work Log
Optional sections: Technical Details, Resources, Notes
File-todos system (this skill): Markdown files in todos/ directory for development/project tracking. Used by humans and agents.
Application Todo model: Database model for user-facing task management. Different from this file-based system.
TodoWrite tool: In-memory task tracking during agent sessions. Temporary, not persisted to disk.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.