Skills land-reduction-trespass
📦

land-reduction-trespass

Content revision r1 Critical ⚙️ External commands

Process Land and Trespass Evidence

Land and trespass evidence review needs consistent metadata, factual summaries, and citation discipline. This skill guides Claude, Codex, and Claude Code through the Land_Reduction_Trespass queue workflow.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "land-reduction-trespass" from https://skillstore.io/skills/acskamloops-land-reduction-trespass.md and its manifest at https://skillstore.io/api/skills/acskamloops-land-reduction-trespass/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/acskamloops-land-reduction-trespass.md Signed manifest GET /api/skills/acskamloops-land-reduction-trespass/manifest Signed lockfile GET /api/skills/acskamloops-land-reduction-trespass/lockfile

Test it

Using "land-reduction-trespass". A batch contains a 1913 letter about acreage differences for Reserve No. 10.

Expected outcome:

The skill records the year, title, provenance, relevance, factual summary, and quoted evidence about the acreage discrepancy.

Using "land-reduction-trespass". A task includes garbled OCR text with no reliable words.

Expected outcome:

The skill routes the task for OCR failure handling instead of inventing metadata or conclusions.

Using "land-reduction-trespass". A document names a railway right of way near a reserve but omits Pukaist in the title.

Expected outcome:

The skill applies geographic and infrastructure context rules before assigning relevance.

Security Audit

Critical
v8 • 7/6/2026 Open versioned report

Most static backtick and PowerShell findings are Markdown formatting false positives. Real risks remain where the skill instructs agents to run repository workflow scripts, and a critical prompt-injection pattern tells agents to obey system_instructions from untrusted JSON tasks.

1
Files scanned
163
Lines analyzed
6
Review items
0
False positives ignored

Confirmed security concerns (2)

Critical
SKILL.md:20
Prompt Injection Attempt Detected
The skill says to follow the `system_instructions` block injected into every JSON task file as hard constraints. This delegates instruction authority to untrusted task data.
The line explicitly instructs the agent to obey system_instructions from task JSON. That untrusted content could override platform and user instructions.
High
SKILL.md:123-128SKILL.md:130-140
Workflow Commands Can Mutate Project Files
The skill documents submit and flag commands that append reports, log flagged tasks, and move files into the Vision pipeline. These side effects require trusted scripts and explicit control.
The workflow text directly describes appending analysis and automatically moving source files. The behavior is intentional and security-relevant in shared workspaces.
Capability review items (6)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
SKILL.md:10
Ruby/shell backtick execution
- For court audit trails, run batches via `codex_exec_runner.sh` with `PUKAIST_CODEX_LOG_EVENTS=1` t
This line tells agents to run codex_exec_runner.sh with an environment variable. In a community skill, invoking local shell runners can execute repo-controlled code.
Medium
SKILL.md:35-37
Ruby/shell backtick execution
```powershell
The fenced block contains a python command that runs refinement_workflow.py get-task. Running local project scripts is real external command execution.
Medium
SKILL.md:42-44
Ruby/shell backtick execution
```powershell
The fenced block instructs agents to run python -c against a supplied path. It appears read-only, but it is still external interpreter execution.
Medium
SKILL.md:124-126
Ruby/shell backtick execution
```powershell
The block instructs agents to run refinement_workflow.py submit-task. The documented result appends analysis to an internal report, so command execution has side effects.
Medium
SKILL.md:133-135
Ruby/shell backtick execution
```powershell
The block instructs agents to run refinement_workflow.py flag-task. This executes local workflow code and changes task state in the workspace.
Medium
SKILL.md:138-140
Ruby/shell backtick execution
```powershell
The block instructs agents to run flag-task for OCR failure. The surrounding text says this automatically moves source files, making the command a real side-effect risk.

Risk Factors

⚙️ External commands (41)
SKILL.md:7 SKILL.md:8 SKILL.md:10 SKILL.md:20 SKILL.md:30 SKILL.md:31 SKILL.md:35-37 SKILL.md:37-40 SKILL.md:40-42 SKILL.md:42-44 SKILL.md:44-62 SKILL.md:62 SKILL.md:63-89 SKILL.md:89-95 SKILL.md:95 SKILL.md:98-102 SKILL.md:102-104 SKILL.md:104-109 SKILL.md:109-112 SKILL.md:112 SKILL.md:119 SKILL.md:120 SKILL.md:121-124 SKILL.md:124-126 SKILL.md:126-127 SKILL.md:127-128 SKILL.md:128 SKILL.md:132-133 SKILL.md:133-135 SKILL.md:135-137 SKILL.md:137-138 SKILL.md:138-140 SKILL.md:140-143 SKILL.md:143 SKILL.md:144-145 SKILL.md:145 SKILL.md:35 SKILL.md:42 SKILL.md:124 SKILL.md:133 SKILL.md:138
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/acskamloops-land-reduction-trespass/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/acskamloops-land-reduction-trespass/security.svg)](https://skillstore.io/skills/acskamloops-land-reduction-trespass?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/acskamloops-land-reduction-trespass?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/acskamloops-land-reduction-trespass/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/acskamloops-land-reduction-trespass.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

ACSKamloops. (2026). land-reduction-trespass security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/acskamloops-land-reduction-trespass/audits/8

BibTeX citation

@techreport{acskamloops-acskamloops-land-reduction-trespass-2026, author = {ACSKamloops}, title = {land-reduction-trespass security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/acskamloops-land-reduction-trespass/audits/8}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "land-reduction-trespass security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "ACSKamloops" date-released: "2026-07-06" url: "https://skillstore.io/skills/acskamloops-land-reduction-trespass/audits/8" identifiers: - type: other value: "skillstore:acskamloops-land-reduction-trespass:audit:8" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
70
Community
91
Spec Compliance

What You Can Build

Review Reserve Evidence

Process task batches about reserve reduction, survey discrepancies, settler encroachment, and railway right-of-way records.

Prepare Manager Review

Create factual task summaries with metadata, relevance, reliability, OCR status, and quoted supporting evidence.

Flag Processing Exceptions

Identify irrelevant, corrupt, OCR-failed, or provenance-failed tasks and route them through the documented workflow.

Try These Prompts

Review the Next Batch 
Use the land-reduction-trespass skill to process the next Land_Reduction_Trespass task batch. Read the JSON input and draft factual results.
Extract Evidence Fields 
Review this task content for reserve reduction, trespass, survey error, or railway taking evidence. Extract metadata, relevance, summary, conclusion, and key evidence.
Validate Before Submission 
Check my draft Land_Reduction_Trespass analysis for missing metadata, weak evidence, banned opinion words, short conclusions, and unsupported dates.
Handle Complex Exceptions 
Evaluate these mixed task results for provenance failure, OCR failure, irrelevance, and manager review readiness. Recommend the correct workflow action for each task.

Best Practices

  • Review every task manually before writing analysis.
  • Use verbatim quotes with page references when evidence is available.
  • Confirm metadata against document text, not only filenames.

Avoid

  • Do not submit opinion words or legal conclusions.
  • Do not rely only on keyword matches.
  • Do not run workflow commands in an untrusted repository.

Frequently Asked Questions

What queue does this skill support?
It supports the Land_Reduction_Trespass queue for land, trespass, survey, and railway taking evidence.
Does it provide legal advice?
No. It produces factual evidence summaries and quoted support for later review.
What input format does it expect?
It expects JSON task files produced by the repository refinement workflow.
Can it read original PDFs directly?
No. The instructions limit work to JSON task content and copied source text.
How does it handle weak OCR?
It routes noisy or unreadable text through the OCR failure workflow instead of guessing.
Why is trusted workspace setup important?
The workflow commands can append reports, log tasks, and move files in the repository.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/ACSKamloops/shs-engine/tree/master/.codex/skills/land-reduction-trespass

Ref

c1fdca50ff516318f65fed0d7f9e82797c5171dc

Maintenance freshness

7/18/2026

Usage

5 downloads · 184 views

File structure

📄 SKILL.md