Security audit

Catalyst Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent catalysis literature-search helper that only asks for web search and fetch access appropriate to its purpose.

Install only if you are comfortable with catalysis search topics being used in web searches and publisher-page fetches. Do not enter confidential, proprietary, or export-controlled research keywords unless your agent environment and search providers are approved for that data.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The README explicitly states that the skill retrieves literature from external web services such as ScienceDirect, arXiv, OpenAlex, and Google Scholar, but it does not disclose that user-supplied topics and prompts may be sent to those third parties. This creates a privacy and data-handling risk because sensitive research interests, proprietary catalyst programs, or internal project keywords could be exposed outside the local environment without informed user consent.
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The guidance explicitly says 'English: use high-IF journals ... and highly cited papers as priority sources,' which imposes a language preference in the skill instructions rather than merely honoring the optional user language preference. Because this is not framed as user-selected or region-specific, it can conflict with language/locale policy expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The Chinese instructions state that English literature and high-IF English journals should be prioritized, even though the input interface says language preference is optional. This creates a default language bias without explicit opt-in or a documented policy reason.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The document is written as a bilingual capability file but is headed and primarily framed in Chinese, with no statement that the user may choose their preferred language. Under the policy for natural-language violations, imposing a specific language or locale without opt-in should be flagged unless a justified regional constraint is documented.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The file title and primary instructional content are presented first in Chinese, and the usage guidance is framed around that bilingual structure without explicitly stating that users may choose their preferred language. This can be a natural-language locale policy issue if the skill is expected to support user choice rather than defaulting to a specific language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The file states that output must be produced strictly in the specified field format, and the template is explicitly bilingual Chinese/English throughout. This can be read as imposing a fixed language/locale format without user opt-in or an offered alternative, which may conflict with language-choice policy expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.