Loading the registry…
When a dispatched agent returns a halt-and-surface finding (ODD violation, fence breach, schema mismatch, novel ambiguity, RF surface, scope tradeoff), the persona applies the four-bucket triage — test against operational objective → categorise as in-scope-resolve / in-scope-defer / out-of-scope-FIDRAFT / owner-escalate → route → close the loop with the agent's status file. Surface-when-meaningful refinement — surface findings to the owner only when they materially change the cycle's outcome shape, an autonomous decision was made, or a commit landed; otherwise resolve silently and log to status. Use whenever a dispatched agent's return carries any halt-and-surface block.
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.
39 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.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'lukeivers/loam (audit-finding-triage)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'lukeivers/loam (audit-finding-triage)' ~/.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
570 findings · 259.3s
v0.3.74
163 findings · 180.8s
v0.1.0
0 findings · 26.0s
v0.1.0
82 findings · 26.1s
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 · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.9s
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 ·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 815 findings across every scanner that examined this package. None of the 39 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 369 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.
215 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FILE_MAGIC_MISMATCH, ASSET_PROMPT_INJECTION, COMPOUND_FIND_EXEC and 9 more · Files: /repo/docs/plans/sealed/readme-restructure-decision-doc-positioning.manifest.yaml, /repo/docs/plans/sealed/token-defaults-optin-skill.manifest.yaml, /repo/docs/plans/sealed/ws-a4-cost-ceiling.md and 137 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
114 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, GLOB_HIDDEN_FILE_TARGETING, AAK-MCP-018 and 4 more · Files: /repo/plugins/dev-sdlc/odd-extractor/tests/fixtures/build-next/no-survey-context/augmented-objectives.yaml, /repo/plugins/dev-sdlc/odd-extractor/tests/test_AC_COMPINT_7_persistence.py, /repo/framework/per-project-pm/tests/test_AC_PPM_6_enqueue_decision.py and 98 more · reported by cisco-skill-scanner, agent-audit-kit
1 Placeholder value — The matched literal is a placeholder or example — the kind of value a scanner reads as a secret and a human reads as a blank to fill in.
Rules: YARA_credential_harvesting_generic · Files: /repo/docs/experiments/release-integration-v0-13-0-hard-smoke.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
92 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/dev-sdlc/skills/component-scaffold-author/SKILL.md, /repo/plugins/dev-sdlc/skills/plan-before-code-author/SKILL.md, /repo/plugins/dev-sdlc/skills/subagent-routing/SKILL.md and 89 more · reported by cisco-skill-scanner
8 FILE_MAGIC_MISMATCH
Files: /repo/framework/dormancy/requirements.txt, /repo/framework/objective-tracker/requirements.txt, /repo/framework/safety-layer/requirements.txt and 3 more · reported by cisco-skill-scanner
4 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/framework/workspace-bootstrap/src/loam/workspace_bootstrap/adapters/slug_collision.py · reported by cisco-skill-scanner
3 AAK-OAUTH-007
Files: plugins/dev-sdlc/odd-extractor/src/loam_odd_extractor/claude_print_synthesis_client.py, framework/workspace-sync/src/loam/workspace_sync/_resolver_client.py, framework/tools/upgrade-merge-resolver/src/loam/upgrade_merge_resolver/__init__.py · reported by agent-audit-kit
3 EXCESSIVE_FILE_COUNT
Files: /repo/framework/hands-off-lifecycle/., /repo/plugins/dev-sdlc/tools/loam-amend/., /repo/framework/workspace-bootstrap/. · reported by cisco-skill-scanner
316 The review call did not complete.
Rules: AAK-SECRET-001, YARA_command_injection_generic, COMPOUND_FIND_EXEC and 29 more · Files: framework/safety-layer/tests/test_AC_SECHK_5_toggle_off.py, framework/safety-layer/tests/test_AC_SECHK_1_secret_pattern_content.py, framework/safety-layer/tests/test_AC_SECHK_S_outcome_altitude.py and 214 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
52 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, HIDDEN_DATA_FILE, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/SKILL.md, /repo/kernel/SKILL.md, /repo/plugins/dev-sdlc/SKILL.md and 43 more · reported by cisco-skill-scanner, nerlo-install-instruction
1 The review budget for this scan was already spent before these findings were reached.
Rules: YARA_credential_harvesting_generic · Files: /repo/docs/experiments/release-integration-v0-13-0-hard-smoke.md · reported by cisco-skill-scanner
Critical risks: credential exposure, command injection, path traversal.
The artifact contains critical findings related to credential exposure, command injection, and path traversal. These findings indicate potential for shell execution, access to sensitive credentials like GitHub and Google API tokens, and unauthorized file system access. Further high-severity findings include potential for system manipulation, reverse shell directives, and network egress. These capabilities warrant thorough review before deployment.
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 AAK-TASKS-003
Files: framework/tools/handsoff-loop/src/handsoff_loop/orchestrator.py, framework/cost-governance/src/loam/cost_governance/rollup.py · reported by agent-audit-kit
2 MANIFEST_DESCRIPTION_TOO_LONG
Files: /repo/plugins/dev-sdlc/skills/skill-promotion-review/SKILL.md, /repo/plugins/loam-skills/skills/handsoff-loop/SKILL.md · reported by cisco-skill-scanner
1 AAK-MCP-018
Files: framework/workspace-bootstrap/src/loam/workspace_bootstrap/adapters/mcp_json_writer.py · reported by agent-audit-kit
1 MANIFEST_INVALID_NAME
Files: /repo/framework/primary-persona/src/loam/primary_persona/keep_pace/SKILL.md · reported by cisco-skill-scanner
Showing 21 of 21; the rest are in the per-scanner reports above.