Security audit

Cyber IR Playbook

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent defensive incident-reporting helper, with some report-output safety flaws users should understand before use.

This skill is reasonable for local defensive IR reporting. Before installing or using it, treat incident data as untrusted, prefer JSON output for sensitive reports, avoid opening generated CSV files directly in spreadsheet software, render Markdown with raw HTML and remote loading disabled, and choose output paths carefully because existing files can be overwritten even with --dry-run.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (3)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/ir_timeline_report.py:75
Finding: CSV Formula Injection in Generated Timeline Reports
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/ir_timeline_report.py:59
Finding: Unescaped Markdown and HTML Injection in Generated Reports
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/ir_timeline_report.py:122
Finding: Dry-Run Mode Performs Filesystem Writes and Can Overwrite Output
Content: View full analysis
None: output_path.parent.mkdir(parents=True, exist_ok=True) if fmt == "json": output_path.write_text(json.dumps(result, indent=2), encoding="utf-8") return ``` ### Technical Analysis The command-line documentation defines `--dry-run` as operating without side effects, but `main()` invokes `render()` regardless of the flag. The selected output file is consequently created or overwritten, and missing parent directories are created. The write uses the normal privileges of the invoking process. There is no explicit overwrite confirmation, exclusive-create mode, or dry-run condition protecting an existing destination. This issue is primarily a safety-contract violation. Exploitation requires influence over command invocation or the output path and does not bypass operating-system access controls. ### Attack Path 1. A user or automation process invokes the script with `--dry-run`, relying on the documented a ...[truncated 846 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.
md
- Run `scripts/ir_timeline_report.py` to generate a deterministic timeline report.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill instructs use of a bundled Python script and reference files, which implies file read/write behavior, but it does not declare any explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can cause the agent runtime to grant or infer broader filesystem access than reviewers or operators expect, increasing the chance of unintended data exposure or artifact overwrites.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The script advertises a --dry-run mode but still creates directories and writes the output artifact unconditionally in render(). That mismatch can cause unintended filesystem changes, overwriting files or polluting working directories in automation pipelines that expect a no-side-effects preview mode.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.