skill-flag — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-flag (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
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.
Add or remove frontmatter fields across multiple SKILL.md files in one shot. No manual editing per file.
ACTION - add or removeSKILLS - space-separated skill names (or --all for every installed skill)FIELD - the full frontmatter line to add or the key to remove (e.g. disable_model_invocation: true)# Add a flag
~/.claude/commands/skill-flag/scripts/flag.sh add "skill1 skill2 skill3" "disable_model_invocation: true"
# Remove a flag
~/.claude/commands/skill-flag/scripts/flag.sh remove "skill1 skill2" "disable_model_invocation"
# Apply to all installed skills
~/.claude/commands/skill-flag/scripts/flag.sh add --all "user_invocable: false"add: inserts the field line before the closing --- of the YAML frontmatter, skipping if the key already existsremove: deletes any line matching the key from the frontmatter blockadded, removed, already-present, already-absent, no-frontmatter, not-found~/.claude/commands/skill-flag/scripts/flag.sh <action> "<skills>" "<field>"Parse the JSON output and present a clean table of what changed.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.