Loading the registry…
goalforge-internal — use entry commands; do not auto-trigger Approach arbitration for SDD hardening. Invoked by goalforge-harden when the spec marks decision-required OR when two or more approaches involve a hard-to-reverse bet. Normalizes each candidate approach into comparable claims along seven axes (objective, assumptions, files touched, sequencing, validation, rollback, cost), cross-reviews them dimension-by-dimension, and emits a decision memo — chosen direction, rejected alternatives with reasons, verification gates for the chosen path. Advisory input to goalforge-harden; does NOT change the human-gated hardened→ready transition. Trigger: goalforge-harden delegates a multi-approach arbitration for a WP, or a user asks to arbitrate competing implementation approaches.
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.
13 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 -- 'truncuso/cogwright (goalforge-arbiter)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'truncuso/cogwright (goalforge-arbiter)' ~/.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
286 findings · 45.8s
v0.3.74
9 findings · 10.2s
v0.1.0
2 findings · 7.6s
v0.1.0
34 findings · 7.6s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.5s
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 · 1.1s
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 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 331 findings across every scanner that examined this package. None of the 13 findings rated critical by their scanner were dismissed.
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.
161 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, opt.nerlo-rules.nerlo-install-run-bundled-artifact and 1 more · Files: /repo/docs/SKILL.md, /repo/packages/goalforge/spec/evals/fixtures/SKILL.md, /repo/packages/goalforge/redecompose/evals/fixtures/ambiguous-feature/wp-01-old/SKILL.md and 77 more · reported by cisco-skill-scanner, nerlo-install-instruction
20 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: FILE_MAGIC_MISMATCH · Files: /repo/packages/goalforge/redecompose/evals/fixtures/ambiguous-feature/wp-02-keep/overview.md, /repo/packages/goalforge/redecompose/evals/fixtures/identity-feature/wp-01-alpha/overview.md, /repo/packages/goalforge/redecompose/evals/fixtures/identity-feature/wp-02-beta/overview.md and 2 more · 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.
57 MANIFEST_MISSING_LICENSE
Files: /repo/packages/goalforge/SKILL.md, /repo/packages/goalforge/run/SKILL.md, /repo/packages/goalforge/interview/SKILL.md and 54 more · reported by cisco-skill-scanner
21 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CONTRIBUTING.md, /repo/packages/goalforge/brief/SKILL.md, /repo/packages/goalforge/execute/SKILL.md and 10 more · reported by nerlo-install-instruction
19 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/goalforge/references/SKILL.md, /repo/packages/goalforge/run/workflows/SKILL.md and 16 more · reported by cisco-skill-scanner
14 FILE_MAGIC_MISMATCH
Files: /repo/packages/goalforge/run/scripts/goalforge-plan-consumer.sh, /repo/plugins/goalforge/skills/run/scripts/goalforge-plan-consumer.sh, /repo/packages/goalforge/scripts/goalforge-stamp-tables.sh and 3 more · reported by cisco-skill-scanner
13 COMPOUND_FIND_EXEC
Files: /repo/packages/goalforge/wayfind/scripts/wayfind-frontier.sh, /repo/packages/goalforge/wayfind/scripts/wayfind-status.sh, /repo/plugins/goalforge/skills/wayfind/scripts/wayfind-frontier.sh and 2 more
Critical shell execution and command injection capabilities identified.
The artifact contains critical findings related to shell execution in multiple scripts, including `wayfind-frontier.sh`, `wayfind-status.sh`, and `goalforge-generate.sh`. High severity command injection vulnerabilities are present in scripts such as `distiller.sh`, `park-render.sh`, and `run.sh`, which could allow arbitrary command execution via user input. Additionally, the artifact includes potential credential access in `goalforge-learning-route.sh` and `ci-lints.sh`, and dynamic code execution capabilities.
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.
6 COMMAND_INJECTION_USER_INPUT
Files: /repo/packages/goalforge/evals/retrospective/cases/distiller.sh, /repo/packages/goalforge/evals/retrospective/cases/park-render.sh, /repo/packages/goalforge/evals/retrospective/run.sh · reported by cisco-skill-scanner
3 AAK-HEALTHCARE-AI-004
Files: INSTALL.md, packages/goalforge/wayfind/SKILL.md, plugins/goalforge/skills/wayfind/SKILL.md · reported by agent-audit-kit
3 AAK-SECRET-004
Files: scripts/ci-lints.sh, packages/goalforge/scripts/goalforge-learning-route.sh, plugins/goalforge/scripts/goalforge-learning-route.sh · reported by agent-audit-kit
3 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/goalforge/., /repo/., /repo/packages/goalforge/. · reported by cisco-skill-scanner
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
2 HIDDEN_DATA_FILE
Files: /repo/plugins/goalforge/.vendored-allowlist.txt · reported by cisco-skill-scanner
2 MANIFEST_INVALID_NAME
Files: /repo/packages/goalforge/references/templates/SKILL.md, /repo/plugins/goalforge/references/templates/SKILL.md · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/packages/goalforge/scripts/goalforge-goal-eval.py, /repo/plugins/goalforge/scripts/goalforge-goal-eval.py · reported by nerlo-behavioral
1 AAK-MARKETPLACE-004
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 COMPOUND_EXTRACT_EXECUTE
Files: /repo/scripts/install.sh · reported by cisco-skill-scanner
1 FIND_EXEC_PATTERN
Files: /repo/scripts/goalforge-generate.sh · reported by cisco-skill-scanner
Showing 25 of 29; the rest are in the per-scanner reports above.