Scan reports · mukul975/Anthropic-Cybersecurity-Skills
analyzing-linux-system-artifacts: scan report
Examine Linux system artifacts (auth logs, cron/systemd persistence, shell history, SSH keys, and system configuration) to uncover evidence of compromise, detect rootkits or backdoors, and reconstruct user/attacker… An automated scan of this public skill from mukul975/Anthropic-Cybersecurity-Skills: security, token cost, spec and clarity, with every finding and its fix.
Result
Verdict
64/100 · grade F
mukul975/Anthropic-Cybersecurity-Skills/skills/analyzing-linux-system-artifacts at 54a7988
Spec 21 · Efficiency 23 · Clarity 20 · Security 0 (each out of 25)
Always loaded 105 tokens · on trigger 3,540 · on demand 3,361
sec/destructivecritical · SKILL.md:209Destructive filesystem command.sec/secret-readwarn · references/api-reference.md:11Touches credential files.sec/persistencewarn · references/api-reference.md:12Installs persistence or edits shell/agent config.sec/persistencewarn · scripts/agent.py:86Installs persistence or edits shell/agent config.sec/secret-readwarn · scripts/agent.py:138Touches credential files.sec/secret-readwarn · SKILL.md:76Touches credential files.sec/persistencewarn · SKILL.md:77Installs persistence or edits shell/agent config.sec/permissionswarn · scripts/agent.py:83Escalates permissions.sec/permissionswarn · SKILL.md:207Escalates permissions.spec/non-portable-keyswarn · SKILL.mdNon-spec frontmatter (domain, subdomain, tags, version, author, nist_csf, mitre_attack). claude.ai and the Skills API reject the upload; move them under `metadata` or drop them.clarity/vagueinfo · SKILL.md22 vague phrases (etc). Replace with concrete thresholds.eff/orphan-fileinfo · references/api-reference.mdreferences/api-reference.md is never mentioned in SKILL.md, so the agent won't know to read it.
Where it comes from
Source
| Fact | Value |
|---|---|
| Repository | mukul975/Anthropic-Cybersecurity-Skills |
| Skill folder | skills/analyzing-linux-system-artifacts |
| Stars | 34,556 |
| License | Apache-2.0 |
| Commit scanned | 54a7988 |
| Scanned | 2026-10-16 |
| Files | 3 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
For maintainers
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/mukul975-analyzing-linux-system-artifacts)
Alternatives
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- Security ReviewExploit sketch, severity and fix for each finding.Loads when the change touches auth, user input, outbound requests, secrets or an LLM feature.5 rules · Code ReviewScan 100$12
- MCP BuilderA small, safe MCP server for your internal API.Loads when the user builds or fixes an MCP server.5 rules · Agent OpsScan 100$12
- Schema DesignerTables, keys and constraints from your domain.Loads when the user designs tables or a data model.5 rules · Data & SQLScan 100$9
Same repository
More from mukul975/Anthropic-Cybersecurity-Skills
- abusing-dpapi-for-credential-accessGrade C76/100
- abusing-shadow-credentials-for-privescGrade B88/100
- achieving-cmmc-level-2-complianceGrade A94/100
- acquiring-disk-image-with-dd-and-dcflddGrade B86/100
- analyzing-active-directory-acl-abuseGrade B83/100
- analyzing-android-malware-with-apktoolGrade B83/100
- analyzing-api-gateway-access-logsGrade B85/100
- analyzing-apt-group-with-mitre-navigatorGrade B83/100
- analyzing-azure-activity-logs-for-threatsGrade B85/100
- analyzing-bootkit-and-rootkit-samplesGrade A94/100
- analyzing-browser-forensics-with-hindsightGrade F59/100
- analyzing-campaign-attribution-evidenceGrade B83/100
FAQ
Questions
- Is analyzing-linux-system-artifacts safe to install?
- 1 critical finding: read before installing. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit 54a7988 on 2026-10-16. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Related
Keep reading
Free tool
Scan your own skill
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.