Security audit

Markdown Table Maker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small Markdown table utility with disclosed, purpose-aligned file conversion behavior, though users should be careful with untrusted table data.

Install only if you need a local Markdown table helper. Avoid converting untrusted CSV or JSON directly into Markdown that will be published or rendered in a sensitive place unless you sanitize or review the generated table first. Also note that some advertised features, such as merge and TSV conversion, are not implemented in the bundled script.

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 (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/table_maker.py:19
Finding: Unescaped Table Values Permit Markdown Content Injection
Content: View full analysis
Remediation: View remediation
` only if HTML is explicitly acceptable; otherwise replace them with spaces or escaped textual sequences. 4. Consider disabling or escaping raw HTML when output may be rendered by systems that permit embedded HTML. 5. Document that generated Markdown must still be sanitized if it is rendered in a security-sensitive web context. 6. Add tests covering pipes, multiline values, backslashes, links, images, and raw HTML in both headers and cells. For example: ```python def escape_md_cell(value): value = str(value) value = value.replace('\\', '\\\\') value = value.replace('|', '\\|') value = value.replace('\r\n', ' ') value = value.replace('\r', ' ') value = value.replace('\n', ' ') return value ``` Call `escape_md_cell` for every header and cell before width calculation and output generation. If generated files are rendered on a website, also apply a trusted Markdown/HTML sanitizer configured to reject unsafe HTML and URL schemes. ]]>

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation description is broad and includes generic triggers like creating or formatting Markdown tables from user needs, which can cause the skill to be invoked in situations beyond the author's likely intent. Overly broad routing increases the chance of accidental activation, unexpected file handling, or the skill being selected over a more appropriate tool, which can amplify downstream safety or data-handling risks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.