Security audit

Cn Meeting Minutes

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow local meeting-minutes generator that reads user-provided meeting text and writes a Markdown report, with no hidden network, persistence, credential, or privilege behavior found.

Install this if you want a Chinese-language, local-only meeting-minutes helper. Be careful when processing meeting files from untrusted sources, and open generated Markdown in a viewer that disables raw HTML and automatic remote-resource loading if the input may be adversarial.

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/meeting_minutes.py:166
Finding: Untrusted Meeting Content Is Written to Markdown Without Escaping
Content: View full analysis
Remediation: View remediation
`, and HTML entities if generated reports may be opened in renderers that support embedded HTML. 3. Consider implementing a dedicated helper that applies the same sanitization policy to every dynamic field: ```python def escape_markdown(value: object) -> str: text = str(value) text = text.replace("&", "&") text = text.replace("<", "<").replace(">", ">") return re.sub(r'([\\`*_{}\[\]()#+.!|~-])', r'\\\1', text) ``` 4. Apply the helper at the output boundary rather than relying only on extraction logic: ```python safe_topic = escape_markdown(topic) minutes += f"- **Meeting topic**: {safe_topic}\n" for point in key_points: minutes += f"- {escape_markdown(point)}\n" ``` 5. If links must be preserved, use an allowlist-based sanitizer that permits only explicitly required Markdown constructs and safe URL schemes. 6. Document that generated reports contain data derived from the input file and recommend opening them in a renderer configured to disable raw HTML and automatic remote-resource loading. 7. Add regression tests using remote-image syntax, HTML tags, nested links, headings, block quotes, and multiline payloads to ensure they are rendered as inert text. ]]>

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The module docstring presents the tool name, description, and usage entirely in Chinese, and the rest of the script continues with Chinese-only prompts and output. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the restriction is explicitly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The natural-language content of the skill documentation is presented only in Chinese, including the description and usage sections. Under the stated policy, forcing a specific language without user opt-in can be a language/locale policy violation unless the regional constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.