Install
$ agentstack add skill-huangpufan-ssot-skill-ssot-audit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
SSOT Audit
You are on a deliberate catch-up: commits, sessions, or protocol versions have drifted ahead of what SSOT/ records, and you have been routed here to close that gap — not to do new work. Pick the one drift signal that applies and read only its catch-up procedure.
Segment large diffs and long transcripts before reading. Loading the full backlog into one context is the failure mode this skill exists to prevent.
Waterline advancement must follow ../ssot-preflight/references/status-protocol.md §7.1 and the upgrade router in references/protocol-upgrades.md. Record an explicit review before advancing tracked_commit, tracked_session, or tracked_skill_version; use an independent $ssot-doctor stop review only for the §7.1 exceptions, including semantic_impact=high protocol upgrades. semantic_impact=none, low, and medium protocol upgrades may be self-reviewed when their checklist is recorded.
Scan the wide window
Run the large-window two-stream scan; closeout sees one batch, you see many, so cross-batch incident concentration and apex/authority drift only become visible here. Emit zero or more move blocks beside each rule at its new location, using the schema and five self-check questions in ../ssot-closeout/references/promotion-rationale.md. Any move with from: apex or to: apex goes through $ssot-doctor stop review; moves that do not touch apex do not.
When this skill runs inside the SSOT-SKILL bundle repo, also harvest each consumer's ## Pending Captures rows with status: deferred-export and relay them into references/protocol-upgrades.md ## Bundle Captures.
If the transcript is lost, park a CAP- row with signal_source: transcript, status: deferred so the gap stays durable.
Load on demand
| Drift signal | Read | |---|---| | tracked_commit behind HEAD, or user asks commit sync | references/commit-audit.md | | User asks conversation / session transcript catch-up | references/conversation-audit.md | | tracked_skill_version behind ssot-preflight protocol version | references/protocol-upgrades.md router, then references/current-upgrade.md or references/archive/index.md as directed | | Bundle-side inbox lookup during protocol-upgrades cadence | references/protocol-upgrades.md ## Bundle Captures | | Audit produced SSOT edits and you need write mechanics | ../ssot-closeout/references/update-routing.md | | Stop-review / health verification of the audit result | ../ssot-doctor/references/doctor.md |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: huangpufan
- Source: huangpufan/SSOT-SKILL
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.