Loading the registry…
Creates and switches to a dedicated branch for a task, deriving the branch name (feature/<id>-…, fix/<id>-…, chore/<id>-…, etc.) from the task's plan or spec — or, when neither exists yet, a single tracker lookup or the bare task id — and setting up remote tracking through the active delivery provider. Works from any state; never blocks on a missing task folder. Thin slash-command wrapper — the full procedure lives in the wf:branch subagent (config resolution, branch derivation, delivery-provider dispatch, index update all happen there). Use directly via /wf:branch <id> for ad-hoc invocation, OR invoke the Task tool with subagent_type wf:branch from another wf:* skill that needs a branch gate (required when called from another skill — bypasses the slash-command's caller-side cost).
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.
10 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'pavel-rp/wf-plugin (branch)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'pavel-rp/wf-plugin (branch)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 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.
v2.0.11
697 findings · 53.4s
v0.3.74
40 findings · 14.7s
v0.1.0
0 findings · 8.5s
v0.1.0
98 findings · 8.6s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.2s
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 21, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-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 835 findings across every scanner that examined this package. None of the 10 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 1 finding 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.
115 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-TAINT-003, FILE_MAGIC_MISMATCH, SOCIAL_ENG_VAGUE_DESCRIPTION and 3 more · Files: plugins/wf/mcp/test/service.test.ts, /repo/plugins/wf-sandbox-testing/experiments/parity/testdata/two-line-unit.stdout.txt, /repo/plugins/wf-sandbox-testing/experiments/parity/testdata/surplus-empty-token.stdout.txt and 52 more · reported by agent-audit-kit, cisco-skill-scanner
8 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: docs/resolver-consumer-inventory.md, /repo/docs/experiment-engine-followups.md, /repo/docs/wf382-ab-experiment-design.md and 3 more · reported by agent-audit-kit, nerlo-install-instruction
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
263 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/wf-host/skills/init/SKILL.md, /repo/plugins/wf-host/skills/qa-host/SKILL.md, /repo/plugins/wf-author-caps/skills/init/SKILL.md and 260 more · reported by cisco-skill-scanner
199 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/wf-host/SKILL.md, /repo/plugins/wf-author-caps/SKILL.md and 196 more · reported by cisco-skill-scanner
91 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/plugins/wf-sandbox-testing/README.md, /repo/plugins/wf-sandbox-testing/accounting/README.md, /repo/plugins/wf-sandbox-testing/assert/README.md and 29 more · reported by nerlo-install-instruction
59 MANIFEST_INVALID_NAME
Files: /repo/plugins/wf-sandbox-testing/assert/scenarios/broken-branch/runs-current/run-2/workspace-snapshot/_local/wf/FAKE-1/SKILL.md, /repo/plugins/wf-sandbox-testing/assert/scenarios/broken-branch/runs-current/run-1/workspace-snapshot/_local/wf/FAKE-1/SKILL.md, /repo/plugins/wf-sandbox-testing/assert/scenarios/demo-branch/runs-current/run-3/workspace-snapshot/_local/wf/FAKE-1/SKILL.md and 56 more · reported by cisco-skill-scanner
52
1 The model gave no reason we were willing to publish, and a verdict without one is not usable evidence.
Rules: MANIFEST_INVALID_NAME · Files: /repo/plugins/wf-core-authoring/capabilities/core-authoring/fixtures/craft-fixtures/name/over-length-skill-name-that-deliberately-exceeds-the-sixty-four-cap/SKILL.md · reported by cisco-skill-scanner
Artifact contains multiple critical command injection and credential harvesting risks.
The artifact includes code that allows for shell command injection via `eval` and `Function` constructor in `runtime.mjs`, and child process execution in `test.mjs`. It also contains patterns indicative of credential harvesting in `selfcheck.sh`. Additionally, there are numerous instances of file system access that could lead to 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.
Files: /repo/plugins/wf/mcp/dist/runtime.mjs, /repo/plugins/wf/mcp/src/resolver/validate-capability.ts, /repo/plugins/wf/mcp/src/resolver/validate-references.ts and 2 more · reported by cisco-skill-scanner
14 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
6 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/plugins/wf/., /repo/plugins/wf-sandbox-testing/corpus/. and 3 more · reported by cisco-skill-scanner
4 COMMAND_INJECTION_EVAL
Files: /repo/plugins/wf/mcp/dist/runtime.mjs · reported by cisco-skill-scanner
3 FIND_EXEC_PATTERN
Files: /repo/plugins/wf-sandbox-testing/experiments/engine/seed-workspace.sh · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/plugins/wf, /repo/plugins/wf-sandbox-testing/accounting, /repo/plugins/wf-sandbox-testing/experiments/engine · reported by cisco-skill-scanner
3 SECRET_PASSWORD_VAR
Files: /repo/plugins/wf-sandbox-testing/experiments/engine/build.sh · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: plugins/wf/skills/qa-gen/SKILL.md, plugins/wf/skills/qa-gen/references/qa-template.md · reported by agent-audit-kit
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/wf/mcp/scripts/test.mjs · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/plugins/wf/mcp/dist/runtime.mjs · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/plugins/wf/mcp/src/resolver/validate-references.ts · reported by cisco-skill-scanner
2 YARA_credential_harvesting_generic
Files: /repo/plugins/wf-sandbox-testing/runner/selfcheck.sh · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: plugins/wf/mcp/package.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugins/wf/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-STDIO-LAUNCHER-INJECT-001
Files: plugins/wf/.mcp.json · reported by agent-audit-kit
1 AAK-SKILL-004
Files: plugins/wf/skills/pr/SKILL.md · reported by agent-audit-kit
Showing 25 of 82; the rest are in the per-scanner reports above.