Kjell Tore Guttormsen
14ecda886c
Sed-pipeline (16 patterns, longest-match-first) sweeper residuelle ultra*-treff i prose, command-narrativ, agent-prompts, hook-kommentarer, doc-prosa. Pipeline-utvidelser fra V4-prompten: - BSD-syntax [[:<:]]ultra[[:>:]] istedenfor \bultra\b (BSD sed mangler \b) - 6 compound-patterns for ultraplan/ultraexecute/ultraresearch/ultrabrief/ ultrareview/ultracontinue uten -local-suffiks - ultra*-stats glob -> trek*-stats glob - Linje-eksklusjon redusert til ultra-cc-architect (Q8); session-state- eksklusjonen var over-protektiv - File-eksklusjon utvidet til settings.json, package.json, plugin.json, hele .claude/-treet (gitignored + V5-territorium) Q8-undantak holdt: architecture-discovery.mjs + project-discovery.mjs urort. Filnavn-konvensjon holdt: .session-state.local.json + *.local.* preservert. Manuell narrative-fix: tests/lib/agent-frontmatter.test.mjs linje 10 mangled "/ultra*-local" til "/voyage*-local" (ingen slik kommando finnes); korrigert til "/trek*". Residualer utenfor scope (V5 handterer): package.json + .claude-plugin/ plugin.json (Step 12-14 versjons-bump). .claude/* er gitignored spec-historikk med tilsiktet BEFORE/AFTER-narrativ. Part of voyage-rebrand session 3 (Wave 4 / Step 10). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
88 lines
3.5 KiB
Markdown
88 lines
3.5 KiB
Markdown
# Security Policy — trekplan
|
|
|
|
## Reporting a vulnerability
|
|
|
|
Open a **private** issue on Forgejo:
|
|
|
|
> https://git.fromaitochitta.com/open/ktg-plugin-marketplace
|
|
|
|
Tag it `security` and mark it private. Do not file public issues for
|
|
unpatched vulnerabilities. There is no SLA — this is a solo-maintained
|
|
plugin — but acknowledged reports are usually triaged within 7 days.
|
|
|
|
## Supported versions
|
|
|
|
Only the **current minor version** receives security fixes. When v3.2.0
|
|
ships, v3.1.x stops receiving patches. Pin to the latest minor and
|
|
update on the next bump.
|
|
|
|
| Version | Supported |
|
|
|---------|-----------|
|
|
| 3.1.x | Yes |
|
|
| 3.0.x | No (upgrade to 3.1.x) |
|
|
| < 3.0 | No |
|
|
|
|
## Scope
|
|
|
|
The plugin's security posture covers:
|
|
|
|
### Plugin-owned hooks (`hooks/scripts/`)
|
|
|
|
| Hook | Trigger | Purpose |
|
|
|------|---------|---------|
|
|
| `pre-bash-executor.mjs` | `PreToolUse` for Bash | BLOCKs known-dangerous shell patterns; WARNs on suspicious ones; fails open on parse errors |
|
|
| `pre-write-executor.mjs` | `PreToolUse` for Write | BLOCKs writes to `.git/hooks/`, `~/.ssh/`, `.env`, and other sensitive paths |
|
|
| `pre-compact-flush.mjs` | `PreCompact` | Flushes `progress.json` from git history before compaction (P0 drift fix); read-only beyond `progress.json` |
|
|
| `session-title.mjs` *(planned, F9)* | `UserPromptSubmit` | Sets session title `voyage:<command>:<slug>` for headless multiplexing |
|
|
|
|
All hooks are zero-dependency Node.js (`.mjs`) scripts and are designed
|
|
to **fail open** — a hook crash never blocks the user's work. Hooks log
|
|
to stderr only; they never write to user files outside their declared
|
|
scope.
|
|
|
|
### Prompt-level denylist (`commands/trekexecute.md`)
|
|
|
|
The execute command embeds a denylist that takes effect even in headless
|
|
sessions where hooks may not fire. This is layer 4 of the defense-in-depth
|
|
model and protects against plan-injected destructive commands.
|
|
|
|
### Validators (`lib/validators/*.mjs`)
|
|
|
|
Read-only. Never write to user files. Used both by hooks and by command
|
|
phases to detect malformed artifacts before they propagate.
|
|
|
|
## Out of scope
|
|
|
|
- **Opt-in upstream architect step.** Any external producer of
|
|
`architecture/overview.md` ships its own security posture. The
|
|
architecture-discovery validator in this plugin treats
|
|
`architecture/overview.md` as an external contract (drift-WARN, never
|
|
drift-FAIL).
|
|
- **LLM output content.** The plugin validates artifact *shape*, not
|
|
artifact *truthfulness*. A plan that passes `plan-validator --strict`
|
|
may still contain hallucinated file paths or unsafe commands; that is
|
|
why `pre-bash-executor` exists.
|
|
- **The Claude Code CLI itself.** Report Claude Code vulnerabilities to
|
|
Anthropic via https://github.com/anthropics/claude-code/issues.
|
|
|
|
## Hardening recommendations
|
|
|
|
For fork-ers handling untrusted task briefs or plans:
|
|
|
|
1. **Set `disableSkillShellExecution: true`** in `~/.claude/settings.json`
|
|
(CC v2.1.91+) to prevent Skills from invoking arbitrary shell.
|
|
2. **Run plan validation in `--strict` mode** before any execute:
|
|
```bash
|
|
node ${CLAUDE_PLUGIN_ROOT}/lib/validators/plan-validator.mjs --strict plan.md
|
|
```
|
|
3. **Review the plan-critic adversarial output** before approving plans
|
|
from external sources — semantic rubric (rule #7) catches deferred
|
|
decisions that an attacker could exploit.
|
|
4. **Pin a CC version floor.** v3.1.0 of this plugin assumes CC ≥
|
|
2.1.85 for the `if`-field on hooks; older CC silently ignores the
|
|
field, weakening the scoping.
|
|
|
|
## Past advisories
|
|
|
|
None as of v3.1.0. This section will list CVE-style entries if any are
|
|
discovered.
|