Loading the registry…
Generate and apply custom macOS folder icons for a directory's subfolders. Use this skill when the user says any variation of "iconify these folders", "give my projects custom icons", "make my Downloads pretty", "this folder of folders is ugly", "add icons to my client folders", or runs `/iconifier`. Also reach for it when the user is staring at a directory of plain blue folders and wants them to look distinct, organized, or branded. The skill inspects existing custom icons on peers and the parent to learn the house style (emoji-on-folder vs SF Symbol vs AI illustration), gathers context from each folder's contents and sibling names, generates a candidate icon per folder, and shows an HTML preview before touching anything. It picks the best generation method available (gpt-image-1 / imagen if an API key is present, otherwise emoji or SF Symbol). macOS only — exits immediately on non-Darwin. If invoked in a directory with subfolders and no other instruction, default target is "every immediate subdirectory".
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'tal/plugin-marketplace (iconifier)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'tal/plugin-marketplace (iconifier)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
2 findings · 1.1s
v2.0.11
96 findings · 19.4s
v0.3.74
19 findings · 3.6s
v0.1.0
2 findings · 6.2s
v0.1.0
2 findings · 6.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.6s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 121 findings across every scanner that examined this package.
Not reviewed is not the same as clean. Those 65 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
4 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/plugins/spotify-web-api/skills/spotify-web-api/examples/SKILL.md, /repo/plugins/plan-refiner/skills/plan-refinement/examples/SKILL.md · reported by cisco-skill-scanner
2 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: TOOL_ABUSE_UNDECLARED_NETWORK, FILE_MAGIC_MISMATCH · Files: /repo/repo/AGENTS.md, /repo/CLAUDE.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
17 HIDDEN_DATA_FILE
Files: /repo/plugins/tal/.codex-plugin/plugin.json, /repo/plugins/karabiner/.codex-plugin/plugin.json, /repo/plugins/og-simplify/.codex-plugin/plugin.json and 6 more · reported by cisco-skill-scanner
16 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, .agents/plugins/marketplace.json · reported by agent-audit-kit
12 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/iconifier/skills/iconifier/scripts/generate_ai_icon.py · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/plugins/iconifier/skills/iconifier/scripts/generate_ai_icon.py · reported by nerlo-behavioral
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 hooks-no-pretooluse
Files: settings.json
65 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-HEALTHCARE-AI-004, TOOL_ABUSE_UNDECLARED_NETWORK, SOCIAL_ENG_MISLEADING_DESC and 4 more · Files: plugins/sort/README.md, plugins/sort/skills/sort/SKILL.md, plugins/plan-refiner/agents/plan-refiner.md and 38 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
Critical findings include credential access and network egress.
The artifact contains critical findings related to potential credential access within Python scripts, which could lead to network egress. High severity findings indicate the presence of sensitive information in marketplace configuration files and further network egress capabilities. Additionally, medium severity findings point to undeclared network requests and potential data exfiltration.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
1 permissions-no-block
Files: settings.json · reported by agentshield
Showing 16 of 16; the rest are in the per-scanner reports above.