PMS Task

• Outcome: Review
• Latest audit: Sep 11, 2026 · 3:55 AM UTC
• Version: 1.0.0

Overview

The skill has a clear task-tracking purpose, but it writes to GitHub and Google Sheets through unsafe shell command templates and fixed identities, so users should review it before installing.

Install only if this workflow is meant for the named PMS repository and the two listed Google Sheets, and if creating issues as roshanasingh4 while recording Tara Singh Kharwad and [e-mail] in Sheets is correct. Before use, add a final confirmation step and implement the GitHub and Sheets writes with safe argument handling and JSON serialization rather than direct shell templates.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

• Location: SKILL.md:36

Finding

Shell Command Injection Through Unescaped Task and Spreadsheet Data

Content

View full analysis

" \ --body "$(cat < ## Steps to Reproduce 1. 2. 3. ## Expected Outcome ## Actual Outcome EOF )" \ --label "bug," \ --assignee roshanasingh4 ``` #### Feature issue creation (`SKILL.md:60-74`) ```bash gh issue create --repo roshanasingh4/apni-pathshala-pms \ --title "" \ --body "$(cat <<EOF ## Feature Request <description> ## Expected Behavior <expected outcome> ## Use Case Why is this feature needed? EOF )" \ --label "enhancement,<priority>" \ --assignee roshanasingh4 ``` #### Task Tracker updates (`SKILL.md:117-128`) ```bash gog sheets append 1O07SzGzQa2FwpkBE7h2SUDWZlxsUpz8DxCpyxKjRi8U "Production!A:K" \ --values-json '[["PMS-TSK-XXX","<title>","Tara Singh Kharwad","DD/MM/YYYY","New","Issue","Low","[e-mail]","<github_url>","",""]]' \ --insert INSERT_ROWS ``` ```bash gog sheets append 1O07SzGzQa2FwpkBE7h2SUDWZlxsUpz8DxCpyxKjRi8U "Production!A:K" \ --values-json '[["PMS-TSK-XXX","<title>","Tara Singh Kharwad","DD/MM/YYYY","New","Feature","Low","[e-mail]","<github_url>","",""]]' \ --insert INSERT_ROWS ``` #### Daily Update Sheet modification (`SKILL.md:153-156`) ```bash # Append to existing content in Column B gog sheets update 1GgRgfVBrF-ReGPRmntT6Cm2BjiLzJ3JiBaC4lMfrMQs "Sheet1!B<row>" \ --values- ...[truncated 3745 chars]

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The manifest explicitly claims the workflow assigns created tasks to roshanasingh4. However, the sheet-update instructions later hard-code the "Assigned To" field as [e-mail], which is a different assignee identity and creates a direct contradiction in the documented intent of who the task is assigned to.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The skill performs external side effects by creating GitHub issues and modifying Google Sheets, but it does not require an explicit confirmation or warning immediately before execution. In an agent setting, this increases the risk of unintended writes, social-engineering-triggered actions, or accidental project data modification from ambiguous user input.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill hard-codes both the reporter name and assignee email as fixed identities, causing all created records to be attributed to specific individuals regardless of the actual requester or intended owner. This creates an integrity and accountability problem, and in this skill’s context it can also misroute work, expose personal data, and enable unauthorized actions to be performed under someone else’s identity in GitHub/Sheets workflows.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The Task ID format is documented as PMS-TSKXXX in the column mapping, but both append examples later use PMS-TSK-XXX. This is an intent/documentation contradiction that could cause inconsistent identifiers across implementations.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low

• Category: Privilege Escalation
• Confidence: 80% confidence

Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · references/pms-overview.md (reported line 52)May include surrounding context.

md

- FORM_CONFIG
- SYSTEM_SETTINGS

**Permissions:**
- VIEW, CREATE, EDIT, DELETE
- APPROVE, REJECT, EXPORT, ASSIGN
- MANAGE_USERS, MANAGE_SETTINGS

Static analysis

No suspicious patterns detected.