Skills/ClawHub/planning-with-files

planning-with-files@3.29.0

CAUTION· install only

Publisher claims: "Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher othmanadi · publishing for 110 daysInstalls 46,874Last detonated 32 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 3.28.2

vet-skills diff planning-with-files 3.28.2 3.29.0

In the sandbox, this version reached for nothing 3.28.2 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-21 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Authorization escalation language. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1: [plan-attest] No task_plan.md found. Create a plan first.
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexec /usr/bin/dirname
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/dirname
0.2sprocessexec /usr/bin/cat
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sfilesystemread ~/.cache/pwf-prog outside project
0.3sfilesystemwrote ~/.cache/pwf-snapshots/plan.h_ye33ez
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.8sfilesystemread ~/.cache/pwf-snapshots/plan.E96fUy · ~/.cache/pwf-prog/22a6bfbcd32e88f7.prog · ~/.cache/pwf-prog · ~/.cache/pwf-snapshots/raw.11OeK5 · ~/.cache/pwf-snapshots/view.5vnGD0 · ~/.cache/pwf-snapshots/source-progress.g051eK outside project
0.8sfilesystemwrote ~/.cache/pwf-snapshots/plan.E96fUy · ~/.cache/pwf-snapshots/source-progress.g051eK · ~/.cache/pwf-snapshots/view.5vnGD0 · ~/.cache/pwf-snapshots/raw.11OeK5 · ~/.cache/pwf-snapshots/progress.n8nzKu · ~/.cache/pwf-snapshots/raw-progress.ELGkJ1
0.8sprocessexec /usr/bin/dirname
0.8sprocessexec /usr/bin/realpath
0.8sprocessexec /usr/bin/mkdir
0.8sprocessexec /usr/bin/chmod
0.8sprocessexec /usr/bin/mktemp
0.8sprocessexec /usr/bin/awk
0.8sprocessexec /usr/bin/cut
0.8sprocessexec /usr/bin/sha256sum
0.8sprocessexec /usr/bin/grep
0.8sprocessexec /usr/bin/sed
0.8sprocessexec /usr/bin/head
0.8sprocessexec /usr/bin/wc
0.8sprocessexec /usr/bin/tr
0.8sprocessexec /usr/bin/rm
0.8sprocessexec /usr/bin/cat
0.8sprocessexec /usr/bin/tail
0.8sprocessbundled script run in the sandbox with no arguments
0.8sprocessexec /usr/bin/dirname
0.8sprocessexited 2: event one of: progress phase_complete error gate_block attest note
0.8sprocessbundled script run in the sandbox with no arguments
0.9sprocessexec /usr/bin/dirname
0.9sprocessexec /usr/bin/awk
0.9sprocessexec /usr/bin/sed
0.9sprocess8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:364 · Fake instruction boundary tag4. Issue Claude Code's native `/loop <interval> <prompt>` (CC primitive, always available).Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/resolve-plan-dir.sh:337 · Process kill command — agent can terminate processes# above already does it; a non-zero status would kill callers running underFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/inject-plan.py:1413 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandscripts/skill-hook.sh:359 · File permission modification command — agent changes file ownership/permissions# chmod intentionally changes st_mode. Freeze the directory object acrossFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/skill-hook.sh:360 · File permission modification command — agent changes file ownership/permissions# that operation, then use the post-chmod identity for every later check.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Authorization escalation languageSKILL.md:389 · Authorization escalation languageThe mode is set by writing a `.mode` file next to the plan (`.planning/<id>/.mode`, or `./.mode` in legacy root mode). `init-session` writes it for you when you pass `--autonomous` or `--gated`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/inject-plan.sh:515 · Process kill command — agent can terminate processes# permanently kill injection at this root over a plan that cannotFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandscripts/inject-plan.sh:128 · Process kill command — agent can terminate processes# a copied project tree) would otherwise kill injection permanently with noFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/set-active-plan.sh:792 · File permission modification command — agent changes file ownership/permissionschmod =rw "${temp_file}" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Python subprocess execution detectedscripts/inject-plan.py:1659 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandscripts/skill-hook.sh:89 · Process kill command — agent can terminate processes# set -u is active: an unset IFS or PATH must not kill the hook.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandscripts/inject-plan.sh:920 · File permission modification command — agent changes file ownership/permissionschmod 700 "$SNAP_ROOT" 2>/dev/null || :Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:307 · npx invocation of non-well-known package — may execute untrusted code| `npx skills add OthmanAdi/planning-with-files` (or ClawHub) | SKILL.md, scripts, templates only | No, follow the manual fallback below |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈10,605 tok
1 file · 34 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim othmanadi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  3. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim othmanadiPropose a patch to the maintainer