security-findings

security-findings is a skill for Claude Code from sbom-tool/gh-guard. It costs 25 tokens per session (1,748 once invoked), scanned A, original, MIT.

A guide for handling security findings from CodeQL, Scorecard, cargo-deny, cargo-audit, and Dependabot. SARIF is a standard file format that lets GitHub display code-scanning results in one place.

In plain words
What is it for?
Use it to find alerts in GitHub, assess severity and source, investigate affected files or dependencies, decide on a response, and track fixes or dismissals.
Why use it?
It gives findings from different tools a common review process and helps distinguish issues that need fixing from false positives or accepted risks.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the gh-guard plugin — 14 skills, 5 commands shipped together

Good fit Use it to find alerts in GitHub, assess severity and source, investigate affected files or dependencies, decide on a response, and track fixes or dismissals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sbom-tool/gh-guard/security-findings
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sbom-tool/gh-guard --skill security-findings
Clone the repo
git clone --depth 1 https://github.com/sbom-tool/gh-guard

Made for: Claude Code.

Or install gh-guard, the plugin that ships this one along with the rest of its 14 skills, 5 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-findings

README.md
[![agentmods](https://agentmods.dev/badge/skills/sbom-tool/gh-guard/security-findings/github.svg)](https://agentmods.dev/skills/sbom-tool/gh-guard/security-findings)
Your own site
<a href="https://agentmods.dev/skills/sbom-tool/gh-guard/security-findings"><img src="https://agentmods.dev/badge/skills/sbom-tool/gh-guard/security-findings/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-findings

Your own site · 80×15
<a href="https://agentmods.dev/skills/sbom-tool/gh-guard/security-findings"><img src="https://agentmods.dev/badge/skills/sbom-tool/gh-guard/security-findings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.01748
Opus 5 $0.00013 $0.00874
Sonnet 5 $0.00005 $0.00350
Haiku 4.5 $0.00003 $0.00175

Measured 9d ago against content hash 4db9b5c639b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

security-findings scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/security-findings/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Findings — SARIF Triage and Response

Multiple gh-guard components produce security findings: CodeQL (static analysis), Scorecard (supply chain posture), cargo-deny (dependency policy), and cargo-audit (vulnerability advisories). This skill covers how to consume, triage, and act on these findings.

Finding Sources

Source Format Destination Update Frequency
CodeQL SARIF GitHub Security > Code scanning Push to main, PRs, weekly
Scorecard SARIF + JSON GitHub Security > Code scanning + api.securityscorecards.dev Push to main, weekly
cargo-deny CI output PR checks (fail/pass) Every PR
cargo-audit CI output PR checks (fail/pass) Every PR
Dependabot Alerts + PRs GitHub Security > Dependabot Continuous

GitHub Security Tab

All SARIF-producing tools upload to GitHub's Code Scanning interface:

  • Security > Code scanning alerts — consolidated view of all findings
  • Each alert has: severity, description, file location, rule ID
  • Alerts track across commits — if you fix the issue, the alert auto-closes
  • Dismiss with reason: false positive, won't fix, used in tests

Triage Workflow

Priority Matrix

Severity Source SLA Action
Critical/High cargo-audit (CVE) Fix within 7 days Upgrade dependency or apply patch
Critical/High CodeQL Fix within 14 days Code change to resolve the finding
Medium Any Fix in next release Plan the fix, track in issues
Low/Informational Any Backlog Review periodically
Scorecard check Scorecard Best effort Improve configuration

Dismissal Policy

Legitimate reasons to dismiss a finding:

  1. False positive — the tool's analysis is incorrect for your context
  2. Won't fix — accepted risk with documented justification
  3. Used in tests — finding is in test code only, not production
  4. Not applicable — the code path is unreachable or the dependency is unused

Read the full file on GitHub · 173 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 173 lines · 25 tokens per session scan A 4db9b5c639b8

Subscribe to this mod's changes

security-findings is a skill published in the GitHub repository sbom-tool/gh-guard (15 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,748 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

apiiro-mcp-secure-prompt

Use the Apiiro MCP tool apiirosecureprompt when Apiiro MCP is configured in the client and the user wants security guidance added to a coding task before implementation. Trigger on secure-prompt via MCP, or when the user asks for security-aware prompt enhancement before coding (auth, new APIs, persistence, secrets…

apiiro/mcp-server · 76 tokens

implementing-github-advanced-security-for-code-scanning

Configure GitHub Advanced Security with CodeQL to perform automated static analysis and vulnerability detection across repositories at enterprise scale.

xalgorix/xalgorix · 34 tokens

bob-egress

List, add, test, enable, disable, or remove Hacker Bob egress profiles from Codex.

vmihalis/hacker-bob · 25 tokens

detecting-typosquatting-packages

Flag misspelled, brandjacked, and typosquatted package names across npm, PyPI, and crates.io before installation using edit-distance, keyboard-proximity, and known-target corpus matching with typomania, OSSGadget, and pypi-scan.

adriannoes/awesome-agentic-ai · 66 tokens

security-expert

Expert-level application security, OWASP Top 10, penetration testing, and security best practices. Use when the user mentions OWASP, pentesting, appsec, vulnerability, encryption, or authentication, or when the task involves Security Principles, OWASP Top 10, Security Domains, or Broken Access Control.

personamanagmentlayer/pcl · 66 tokens

codeinspectus-fix-one

Investigate and remediate exactly one user-selected CodeInspectus finding with evidence-gated reproduction, a separately approved minimal patch, focused regression testing, and an exact-prior-scan rescan. Use when a user asks an agent to examine, reproduce, fix, or verify one CodeInspectus finding without batching…

Synvoya/codeinspectus · 76 tokens