reject-job — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited reject-job (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.
Manage the remote jobs blocklist. Jobs on this list are filtered out of all future remote job emails.
The blocklist lives in remote_search/rejected_remote.json and is managed via remote_search/reject_remote.py (run from the project root).
Reject a specific job — run the script with company name and job title as arguments.
Reject all roles from a company — run the script with the company name and an empty string as the title.
Reject everything from the last email — run the script with --all. This bulk-rejects all jobs from previous_jobs.json (the last run).
Restore a rejected job — run the script with --remove followed by the company and title.
Show all rejections — run the script with --list.
--remove with the exact same strings used when adding.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.