Audit local
Skill keep-starknet-strange/starknet-skills/.claude/skills/audit-local
Run a local security audit on a Cairo repositoryFrom its SKILL.md
npx -y skills add keep-starknet-strange/starknet-skills --skill audit-localAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.7 KB, as published. Nobody here has run it
Audit Local Skill
Quick Start
-
Validate and sanitize the target repo path:
REPO="$ARGUMENTS" [ -n "$REPO" ] || { echo "ERROR: repo path is required" >&2; exit 1; } echo "$REPO" | grep -qE '^[A-Za-z0-9_./ -]+$' || { echo "ERROR: repo path contains unsafe characters" >&2 exit 1 } if echo "$REPO" | grep -qE '(^|/)\.\.(/|$)'; then echo "ERROR: repo path traversal is not allowed" >&2 exit 1 fi [ -f scripts/quality/audit_local_repo.py ] || { echo "ERROR: scripts/quality/audit_local_repo.py not found from current working directory" >&2 exit 1 } [ -d "$REPO" ] || { echo "ERROR: '$REPO' is not a directory" >&2; exit 1; } -
Run the local deterministic audit:
python3 scripts/quality/audit_local_repo.py --repo-root "$REPO" --scan-id "local-$(date +%s)" -
Report findings grouped by severity (
Critical > High > Medium > Low > Info) with title, location, and fix. -
Summarize totals and top-3 highest-severity findings.
-
Follow the full workflow: Audit Local Workflow
When to Use
- You need a fast deterministic baseline scan on a local Cairo repo.
- You want report artifacts (
.json,.md, optional findings JSONL) for triage.
When NOT to Use
- You need deep multi-agent reasoning over complex economic logic.
- You are auditing non-Cairo targets or unrelated infrastructure.
Rationalizations to Reject
- "No findings means secure."
- "It compiled, so access control must be correct."
- "This can wait until after merge."