Loading the registry…
OpenCode Expert Pack - Execution layer for automated product development
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.
266 critical findings reported by cisco-skill-scanner, agent-audit-kit, 15 of them in the installed artifact. 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 -- opencode-expert-pack
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- opencode-expert-pack ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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
0 findings · 0.7s
v2.0.11
2517 findings · 68.1s
v0.3.74
161 findings · 19.0s
v0.1.0
1 finding · 9.3s
v0.1.0
6 findings · 9.4s
vv0.3.2
Incomplete run
0 findings · 0.5s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.1s
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 ·!: incompletenerlo-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 2,685 findings across every scanner that examined this package. None of the 266 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 2,067 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.
244 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-IPI-WILD-CORPUS-001, SOCIAL_ENG_VAGUE_DESCRIPTION, HIDDEN_DATA_FILE · Files: specs/006-reviewer-core/examples/rejection-with-feedback-example.md, specs/044-github-issue-reporter/examples/cli-usage.md, .opencode/skills/architect/migration-planning/examples/example-001-schema-migration.md and 238 more · reported by agent-audit-kit, cisco-skill-scanner
191 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: DATA_EXFIL_JS_FS_ACCESS, AAK-SECRET-004, SECRET_JWT_TOKEN and 5 more · Files: /repo/tests/e2e/helpers/report-generator.js, /repo/tests/integration/github-issue-reporter/workflow.test.js, /repo/tests/integration/secrets-redaction/integration.test.js and 23 more · reported by cisco-skill-scanner, agent-audit-kit
The model could have called any of these a false positive and did not.
169 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/adapters/github-issue/issue-context.js, /repo/adapters/github-pr/index.js, /repo/adapters/local-repo/index.js and 27 more · reported by cisco-skill-scanner
9 LOW_ANALYZABILITY
Files: /repo/adapters/platform, /repo/adapters/cli-local, /repo/adapters/openclaw and 6 more · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/adapters/github-issue/types.js · reported by cisco-skill-scanner
1 AAK-MCP-OPENCLAW-CVE-2026-62195-001
Files: package.json · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/adapters/github-issue/git-client.js · reported by nerlo-behavioral
1 SECRET_JWT_TOKEN
Files: /repo/lib/secrets-redaction/patterns.js · reported by cisco-skill-scanner
1,264 The review budget for this scan was already spent before these findings were reached.
Rules: HIDDEN_DATA_FILE, EXCESSIVE_FILE_COUNT, AAK-SUPPLY-005 and 3 more · Files: /repo/.opencode/skills/tester/regression-analysis/anti-examples/anti-example-002-no-historical-context.md, /repo/templates/pack/minimal/.opencode/skills/tester/regression-analysis/anti-examples/anti-example-002-no-historical-context.md, /repo/templates/pack/full/.opencode/skills/tester/regression-analysis/anti-examples/anti-example-002-no-historical-context.md and 800 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
491 The model's answer could not be read.
Rules: SECRET_GITHUB_TOKEN, AAK-SECRET-008, YARA_credential_harvesting_generic and 9 more · Files: /repo/tests/integration/secrets-redaction/integration.test.js, /repo/tests/unit/secrets-redaction/false-rates.test.js, /repo/tests/unit/secrets-redaction/patterns.test.js and 245 more · reported by cisco-skill-scanner, agent-audit-kit
312 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-IPI-WILD-CORPUS-001, SOCIAL_ENG_VAGUE_DESCRIPTION, HIDDEN_DATA_FILE · Files: .opencode/skills/architect/migration-planning/anti-examples/anti-example-001-no-rollback-plan.md, templates/pack/full/.opencode/skills/architect/migration-planning/anti-examples/anti-example-001-no-rollback-plan.md, adapters/github-issue/README.md and 303 more · reported by agent-audit-kit, cisco-skill-scanner
Critical risks: credential exposure, command execution, and data exfiltration.
The artifact contains multiple critical findings, including hardcoded credentials such as GitHub tokens and AWS keys, which could lead to unauthorized access. It also exhibits capabilities for command injection via JavaScript child processes and `eval`, posing a risk of arbitrary code execution. Furthermore, the artifact has potential for SQL injection and data exfiltration through file system access.
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.
Showing 25 of 25; the rest are in the per-scanner reports above.