ton-vulnerability-scanner Eval
==============================

Status: failed
Score: 72/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Audit score: Risky

Install:
npx skills add trailofbits/skills --skill ton-vulnerability-scanner

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- FAIL Audit score: Risky
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: CC-BY-SA-4.0
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
- Inconsistency between the description (mentions integer-as-boolean misuse, fake Jetton contracts, forward TON without gas checks) and the SKILL.md pattern summary (Missing Sender Check, Integer Overflow, Improper Gas Handling). The detailed patterns file includes 'Integer as Boolean' but not 'fake Jetton' or 'forward TON without gas checks' explicitly.
- The SKILL.md pattern summary lists three different patterns than the description, which may confuse users about what the skill actually checks.
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- Inconsistency between the description (mentions integer-as-boolean misuse, fake Jetton contracts, forward TON without gas checks) and the SKILL.md pattern summary (Missing Sender Check, Integer Overflow, Improper Gas Handling). The detailed patterns file includes 'Integer as Boolean' but not 'fake Jetton' or 'forward TON without gas checks' explicitly.
- Audit risk risky exceeds max_risk=medium
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required

URLs:
- Skill: https://www.openagentskill.com/skills/trailofbits-ton-vulnerability-scanner
- Audit: https://www.openagentskill.com/skills/trailofbits-ton-vulnerability-scanner/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=trailofbits-ton-vulnerability-scanner