Risk Audit
Absolute safety gate for every Solana token. Runs a fail-closed checklist and returns only CLEAR, CONDITIONAL, or KILL. Used exclusively by the RISK Bot. A KILL cannot be overridden.
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Risk Audit when an AI agent needs a reusable SKILL.md workflow for this job: Absolute safety gate for every Solana token. Runs a fail-closed checklist and returns only CLEAR, CONDITIONAL, or KILL. Used exclusively by the RISK Bot. A KILL cannot be overridden.
When not to use it
Skip Risk Audit when the task is outside the writing category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/risk-audit # Save SKILL.md to ~/.claude/skills/risk-audit/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/risk-audit/SKILL.md. For a shared project, commit the folder at .claude/skills/risk-audit/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Risk Audit skill for this task: Use Risk Audit when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
69/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 56/100
- Source signals
- 72/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Risk Audit
## L1 - Summary The absolute safety gate for every token. RISK runs a fail-closed ten-check checklist and returns exactly one verdict: CLEAR, CONDITIONAL, or KILL. A KILL ends the token path permanently and cannot be overridden.
## L2 - Method 1. Run every check, every time, with the preferred tool path (operator registry; `pumpgrok tools <id> --help` prints the schema): ```bash pumpgrok tools onchain.authorities --help ``` Parse the JSON. If `hasMintAuthority` or `hasFreezeAuthority` is true, that is a strong KILL signal. 2. Mandatory checklist: - Mint authority: must be null / revoked. - Freeze authority: must be null / revoked. - LP status: burned or locked for 6-12 months; quantify the percentage. - Sell / transfer tax: preferably 0 %; hard fail above 5-10 %. - Honeypot / cannot-sell indicators. - Top-10 holders (ex-LP) concentration: flag above 20-25 %. - Bundler / insider cluster detection. - Deployer wallet history if visible. - Token-2022 extensions: document any. - Liquidity depth relative to intended size. 3. Emit the output schema: ``` LEAD / TICKET-ID: ... Verdict: CLEAR | CONDITIONAL | KILL Residual Risks: 1. ... Evidence: [source plus UTC] Conditions (if CONDITIONAL): ... Self-Audit: All 10 checks completed: YES / NO ```
## Failure modes - Any check cannot be completed with live data: the verdict is not CLEAR. Incomplete evidence is CONDITIONAL at best, KILL when the gap hides catastrophic risk. - Narrative or FOMO pressure to soften: never soften a KILL; no other Bot may proceed past one. - Skipped or approximated check: re-run. The self-audit line must read YES.
## References - Tools: `onchain.authorities`, `onchain.top_holders` (operator registry); port: `src/pumpgrok/tools/onchain/` - Gate: G-2; veto: absolute, non-appealable (`desk-operating-model`)
Intended uses
- Use Risk Audit when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.