Loading the registry…
Model-conditional ad screening, evidence-grounded audience panels, real-world study preparation, uploaded aggregate result import, deterministic scoring, and marketer-ready HTML dashboards.
Gemini Extensions are packaged skills loaded into Gemini; 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.
23 critical findings reported by cisco-skill-scanner, agent-audit-kit, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/innovaitionpartners/audience-ad-testing-lab, 122 findings
Gemini Extensions install to a single target, no runtime picker.
nerlo install -- audience-ad-testing-lab
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.
v2.0.11
68 findings · 33.3s
v0.3.74
51 findings · 107.4s
v0.2.0
0 findings · 34.1s
v0.2.0
3 findings · 34.1s
v0.1.0
0 findings · 90.5s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.1s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Oct 4, 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: complete | rejected |
| Aug 11, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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 122 findings across every scanner that examined this package. 21 of 23 findings rated critical by their scanner were among the dismissals.
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.
54 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-SECRET-003, SECRET_AWS_KEY, COMMAND_INJECTION_EVAL and 4 more · Files: conformance/test_real_world_outcome_data_prep_source_safety.py, /repo/conformance/test_real_world_outcome_data_prep_source_safety.py, /repo/conformance/test_experimental_calibration_simulation.py and 34 more · reported by agent-audit-kit, cisco-skill-scanner
12 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/docs/SKILL.md, /repo/docs/concepts/SKILL.md, /repo/docs/guides/SKILL.md and 3 more · reported by cisco-skill-scanner
3 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/.github/actions/setup-private-stage/action.yml · reported by 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.
14 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/skills/audience-data-lab/scripts/audience_data_lab/authorized_source.py, /repo/skills/audience-ad-testing-lab/scripts/audience_lab/audience_library.py, /repo/skills/audience-panel-builder/scripts/audience_panel_builder/population/validation/library.py · reported by cisco-skill-scanner
12 AAK-HEALTHCARE-AI-004
Files: skills/audience-panel-builder/README.md, skills/audience-panel-builder/SKILL.md, skills/real-world-outcome-data-prep/SKILL.md and 9 more · reported by agent-audit-kit
10 MANIFEST_MISSING_LICENSE
Files: /repo/skills/audience-data-lab/SKILL.md, /repo/skills/audience-panel-builder/SKILL.md, /repo/skills/real-world-outcome-data-prep/SKILL.md and 7 more · reported by cisco-skill-scanner
7 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/skills/audience-data-lab/references/SKILL.md, /repo/skills/audience-ad-testing-lab/references/SKILL.md and 4 more · reported by cisco-skill-scanner
2 AAK-MARKETPLACE-001
The model could have called any of these a false positive and did not.
2 OBFUSCATION_XOR_ENCODING
Files: /repo/skills/audience-ad-testing-lab/scripts/claude-large-panel-workflow.mjs · reported by cisco-skill-scanner
Critical command injection and high resource abuse risks identified.
The artifact contains critical command injection vulnerabilities in `/repo/skills/audience-ad-testing-lab/scripts/claude-large-panel-workflow.mjs`, allowing for shell execution. Multiple high-severity resource abuse findings, indicating potential infinite loops, are present across several Python files. Additionally, high-severity issues related to marketplace plugin definitions are noted in `.agents/plugins/marketplace.json` and `.claude-plugin/marketplace.json`.
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.
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/skills/audience-ad-testing-lab/scripts/claude-large-panel-workflow.mjs · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/skills/audience-panel-builder/. · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/.agents/plugins/marketplace.json, /repo/.codex-plugin/plugin.json · reported by cisco-skill-scanner