Reads, searches and exports local OpenAI Codex history without continuing work: session inventory, timelines, verbatim user input, indexed search, and rollout identity/fork lineage. Use when the user asks what they told Codex, wants a Session ID, or evidence of what a run did. Not for Claude Code (use read-claude-code-history); with no platform named, start at local-conversation-history.
- Stars
- 1,540
- Version
- v3
- Copies
- 0
Overview
Waxell rates it high risk: 50 findings, highest severity high.
- Highest severity
- high
- Findings
- 50
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked 2 days ago
Result
High risk Waxell rates it high risk: 50 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (50)
high · 18
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:93 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:283 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:301 · skillspector:AE1
- high
Data Exfiltration: Context Leakage
scripts/read_codex_session.py:2374 · skillspector:E4
- high
Data Exfiltration: Env Variable Harvesting
tests/test_analyze_sessions.py:98 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_analyze_sessions.py:1379 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_list_codex_user_inputs.py:36 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_list_local_history.py:135 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_analyze_sessions.py:1417 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_analyze_sessions.py:1467 · skillspector:E2
- high
Dangerous Code Execution: exec() call detected
tests/test_find_codex_session.py:162 · skillspector:AST1
- high
Data Exfiltration: Env Variable Harvesting
tests/test_list_local_history.py:1668 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_paginated_lineage.py:131 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_paginated_lineage.py:149 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_paginated_lineage.py:155 · skillspector:E2
- high
Data Exfiltration: Env Variable Harvesting
tests/test_reader_metadata_lookup.py:281 · skillspector:E2
- high
Privilege Escalation: Credential Access
tests/test_read_codex_session.py:789 · skillspector:PE3
- high
Data Exfiltration: Env Variable Harvesting
tests/test_reconcile_codex_inputs.py:60 · skillspector:E2
medium · 32
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Data Exfiltration: File System Enumeration
scripts/_core/homes.py:83 · skillspector:E3
- medium
Dangerous Code Execution: subprocess module call
scripts/_core/text.py:535 · skillspector:AST4
- medium
Output Handling: Unbounded Output
scripts/analyze_sessions.py:2089 · skillspector:OH3
- medium
Output Handling: Unbounded Output
scripts/read_codex_session.py:1560 · skillspector:OH3
- medium
Dangerous Code Execution: subprocess module call
scripts/read_codex_session.py:1634 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'project_path' from os.environ.get (line 2100, credential/environment) → subprocess.run (code e
scripts/read_codex_session.py:1634 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
tests/test_analyze_sessions.py:102 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_analyze_sessions.py:1384 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_analyze_sessions.py:1420 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_analyze_sessions.py:1465 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_find_codex_session.py:53 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_find_codex_session.py:147 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_codex_user_inputs.py:38 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:138 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:328 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1090 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1130 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1157 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1167 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1171 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1174 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_list_local_history.py:1653 · skillspector:AST4
- medium
Suspicious Unicode normalization or mixed-script content
tests/test_paginated_lineage.py:1 · skillspector:AE4
- medium
Dangerous Code Execution: subprocess module call
tests/test_paginated_lineage.py:131 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_paginated_lineage.py:149 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_paginated_lineage.py:155 · skillspector:AST4
- medium
Rogue Agent: Session Persistence
tests/test_read_codex_session.py:48 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
tests/test_read_codex_session.py:48 · skillspector:RA2
- medium
Dangerous Code Execution: subprocess module call
tests/test_reader_metadata_lookup.py:279 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_reconcile_codex_inputs.py:58 · skillspector:AST4
- medium
Agent Snooping: Skill Enumeration
tests/test_reconcile_codex_inputs.py:406 · skillspector:AS3
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v32026-11-194 changed High riskgot riskier
- v22026-11-166 changed No issues
- v12026-11-03 No issues
Files
Files
39 files, 845 KB in total. Names only; open them on GitHub.
- SKILL.md
- evals/evals.json
- references/codex_rollout_format.md
- references/legacy_multi_provider_inventory.md
- references/session-lookup.md
- references/storage_and_portability.md
- references/terminal-session-recovery.md
- references/user_input_reconciliation.md
- scripts/_core/__init__.py
- scripts/_core/claude.py
- scripts/_core/codex.py
- scripts/_core/homes.py
- scripts/_core/kimi.py
- scripts/_core/model.py
- scripts/_core/native_output.py
- scripts/_core/parse.py
- scripts/_core/sources.py
- scripts/_core/text.py
- scripts/analyze_sessions.py
- scripts/find_codex_session.py
- scripts/list_codex_user_inputs.py
- scripts/list_local_history.py
- scripts/prompt_cursor.py
- scripts/read_codex_session.py
- scripts/reconcile_codex_inputs.py
- tests/test_analyze_sessions.py
- tests/test_find_codex_session.py
- tests/test_kimi_provider.py
- tests/test_list_codex_user_inputs.py
- tests/test_list_local_history.py
- tests/test_native_output.py
- tests/test_original_record_evidence.py
- tests/test_paginated_lineage.py
- tests/test_pre_envelope_rollout.py
- tests/test_prompt_cursor.py
- tests/test_read_codex_session.py
- tests/test_reader_metadata_lookup.py
- tests/test_reconcile_codex_inputs.py
- tests/test_streaming_validation.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
local-codexdaymadeLaunches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate… High riskEngineeringAI & agents1.5k
macos-cleanerdaymadeDiagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign… High riskEngineeringData & analytics1.5k
macos-watchdogdaymadeDesigns and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications,… High riskEngineeringDesign1.5k
skill-governancedaymadeGoverns Claude Code/Codex/Antigravity Skill surfaces: reconciles source/install/catalog-visibility drift and adaptive hot/cold evolution… High riskEngineeringAI & agents1.5k