Loading the registry…
Iterate on a traced function to improve pass rates using failed traces, labeling, and replay; also replays a single trace to check whether a fix worked. TRIGGER when: user explicitly asks Bitfab for help improving or optimizing a traced function in any way (quality, pass rate, token usage, cost: 'use bitfab to ...', 'can bitfab help me ...'), wants to fix failing AI outputs, improve pass rates, reduce token usage or LLM cost of a traced function against a dataset, debug LLM behavior, iterate on prompts, label traces, run experiments, benchmark or score a dataset against the current code, run a regression test, run a dedicated cost-optimization pass that profiles token spend and iterates to cut it, add a trace to a dataset, fix a bug **in a traced function starting from its failing Bitfab trace**, or replay/re-run one specific trace to verify a change; says anything like 'fix my AI', 'improve pass rate', 'fix this trace', 'fix trace <id>', 'fix this failing trace and lock it in as a test', 'use bitfab to reduce token usage', 'cut tokens on this dataset', 'lower the token cost of my traced function', 'cost optimize generate-email', 'optimize the cost of this function', 'why is this failing', 'iterate on traces', 'debug my agent', 'review traces', 'benchmark my dataset', 'run my dataset as a benchmark', 'how does my code score on this dataset', 'evaluate the dataset without changing anything', 'add a trace to a dataset', 'attach traces to a dataset', 'replay this trace', 'rerun trace <id>', 'did my fix work', 'does this trace pass now', 'check if my change fixed <id>', 'show experiments for a dataset', 'list experiments that ran on this dataset', 'what experiments used dataset <id>', 'open the experiments for <dataset>'. SKIP when: user wants to instrument new code or set up tracing (use bitfab:setup instead), or wants generic token/cost/code optimization that mentions none of Bitfab, traces, or datasets. A bare 'fix this bug' / 'fix X' that is not anchored to a specif
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.
69 critical findings reported by cisco-skill-scanner, agent-audit-kit, 65 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 -- 'project-white-rabbit/bitfab-codex-plugin (assistant)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'project-white-rabbit/bitfab-codex-plugin (assistant)' ~/.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
826 findings · 171.9s
v0.3.74
6 findings · 22.0s
v0.1.0
0 findings · 16.3s
v0.1.0
2 findings · 16.3s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.7s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.3s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.6s
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 22, 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 834 findings across every scanner that examined this package. 4 of 69 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 2 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.
184 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: COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR, DATA_EXFIL_JS_FS_ACCESS, SECRET_CONNECTION_STRING and 2 more · Files: /repo/plugins/bitfab/node_modules/zod/src/v4/classic/tests/jitless-allows-eval.test.ts, /repo/plugins/bitfab/dist/codexSessionRuntime.test.js, /repo/plugins/bitfab/node_modules/bitfab-plugin-lib/dist/activePreviewSession.test.js and 37 more · reported by cisco-skill-scanner
6 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: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_INVALID_NAME, MANIFEST_MISSING_LICENSE · Files: /repo/plugins/bitfab/node_modules/function-bind/.github/SKILL.md, /repo/plugins/bitfab/node_modules/qs/.github/SKILL.md · reported by cisco-skill-scanner
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.
131 DATA_EXFIL_JS_NETWORK
Files: /repo/plugins/bitfab/node_modules/@modelcontextprotocol/sdk/dist/cjs/server/webStandardStreamableHttp.d.ts, /repo/plugins/bitfab/node_modules/@modelcontextprotocol/sdk/dist/cjs/server/webStandardStreamableHttp.js, /repo/plugins/bitfab/node_modules/@modelcontextprotocol/sdk/dist/esm/server/webStandardStreamableHttp.d.ts and 41 more · reported by cisco-skill-scanner
98 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/bitfab/skills/assistant/SKILL.md, /repo/plugins/bitfab/skills/setup/SKILL.md, /repo/plugins/bitfab/skills/update/SKILL.md and 95 more · reported by cisco-skill-scanner
95 LOW_ANALYZABILITY
Files: /repo/plugins/bitfab/node_modules/depd, /repo/plugins/bitfab/node_modules/path-to-regexp, /repo/plugins/bitfab/node_modules/mime-types and 92 more · reported by cisco-skill-scanner
95 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/plugins/bitfab/SKILL.md, /repo/plugins/bitfab/node_modules/side-channel-map/SKILL.md, /repo/plugins/bitfab/node_modules/serve-static/SKILL.md and 92 more · reported by cisco-skill-scanner
61 DATA_EXFIL_JS_FS_ACCESS
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_EXECUTABLE_SCRIPT · Files: /repo/plugins/bitfab/node_modules/ajv/.runkit_example.js · reported by cisco-skill-scanner
Critical command injection and credential access risks identified.
This artifact contains critical findings related to command injection via JavaScript function constructors, eval, and child process execution. It also exhibits potential for credential access and path traversal. Additionally, the artifact can perform file system access and network egress, which warrant attention.
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/bitfab/dist/codexSessionRuntime.js, /repo/plugins/bitfab/dist/version.js, /repo/plugins/bitfab/node_modules/bitfab-plugin-lib/dist/activePreviewSession.js and 25 more · reported by cisco-skill-scanner
40 FILE_MAGIC_MISMATCH
Files: /repo/plugins/bitfab/node_modules/hono/dist/adapter/netlify/index.js, /repo/plugins/bitfab/node_modules/zod-to-json-schema/dist/esm/index.js, /repo/plugins/bitfab/node_modules/zod/v4/core/index.js and 21 more · reported by cisco-skill-scanner
37 HIDDEN_DATA_FILE
Files: /repo/plugins/bitfab/node_modules/side-channel-map/.nycrc, /repo/plugins/bitfab/node_modules/has-symbols/.nycrc, /repo/plugins/bitfab/node_modules/side-channel-list/.nycrc and 18 more · reported by cisco-skill-scanner
24 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/plugins/bitfab/node_modules/ajv/dist/compile/index.js, /repo/plugins/bitfab/node_modules/ajv/dist/compile/jtd/parse.js, /repo/plugins/bitfab/node_modules/ajv/dist/compile/jtd/serialize.js and 9 more · reported by cisco-skill-scanner
20 COMMAND_INJECTION_EVAL
Files: /repo/plugins/bitfab/node_modules/ajv/dist/core.js, /repo/plugins/bitfab/node_modules/ajv/dist/standalone/instance.js, /repo/plugins/bitfab/node_modules/path-to-regexp/dist/index.js and 6 more · reported by cisco-skill-scanner
15 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/bitfab/node_modules/bitfab-plugin-lib/dist/browser.js, /repo/plugins/bitfab/node_modules/bitfab-plugin-lib/dist/commands/update.js, /repo/plugins/bitfab/node_modules/cross-spawn/index.js and 1 more · reported by cisco-skill-scanner
6 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/bitfab/node_modules/hono/., /repo/plugins/bitfab/node_modules/zod-to-json-schema/., /repo/plugins/bitfab/node_modules/@modelcontextprotocol/sdk/. and 3 more · reported by cisco-skill-scanner
4 YARA_code_execution_generic
Files: /repo/plugins/bitfab/node_modules/ajv-formats/dist/formats.js, /repo/plugins/bitfab/node_modules/ajv-formats/src/formats.ts · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: plugins/bitfab/skills/assistant/SKILL.md, plugins/bitfab/skills/setup/SKILL.md · reported by agent-audit-kit
2 MANIFEST_DESCRIPTION_TOO_LONG
Files: /repo/plugins/bitfab/skills/assistant/SKILL.md, /repo/plugins/bitfab/skills/setup/SKILL.md · reported by cisco-skill-scanner
2 YARA_coercive_injection_generic
Files: /repo/plugins/bitfab/node_modules/jose/dist/types/types.d.ts · reported by cisco-skill-scanner
2 YARA_credential_harvesting_generic
Files: /repo/plugins/bitfab/node_modules/jose/dist/webapi/key/import.js · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .agents/plugins/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugins/bitfab/mcp.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: plugins/bitfab/scripts/build-skill-shims.mjs · reported by agent-audit-kit
1 AAK-SKILL-003
Files: plugins/bitfab/skills/setup/SKILL.md · reported by agent-audit-kit
1 MANIFEST_INVALID_NAME
Files: /repo/plugins/bitfab/node_modules/ipaddr.js/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/plugins/bitfab/README.md · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/plugins/bitfab/scripts/install-session-hook.mjs · reported by nerlo-install-instruction
1 PROMPT_INJECTION_CONCEALMENT
Files: /repo/plugins/bitfab/skills/setup/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 182; the rest are in the per-scanner reports above.