search — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited search (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
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.
Look up a company or job URL in List.xlsx (Sheet1). Rejected applications are rows on Sheet1 with status Rejected and strikethrough; the old separate "Rejected" sheet was merged into Sheet1 on 2026-09-25.
Run the script from the project root (claude-job-agent/):
python .claude/skills/search/scripts/search_tracker.py "Company Name"
python .claude/skills/search/scripts/search_tracker.py "https://job-url"Add --json for machine-readable output.
The script is read-only. It:
query in company or company in query), skipping empty cells=HYPERLINK(...) formulas, ignoring www, query strings, trailing slashes and /thanks or /application suffixesShow the script output to the user. Do not write ad hoc openpyxl code for searches.
done / applied → ✅ Appliedin progress / under review → 🕐 In Progressrejected → ❌ Rejectednot available / nothing to apply → ⏸️ No Jobs Available~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.