Security audit

Academic Deep Research 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This research skill is mostly purpose-aligned, but it under-discloses network use and reads persistent memory by default without clear user consent.

Install only if you are comfortable with the agent searching the web, fetching external pages, potentially spawning parallel research agents, and consulting prior memory. Avoid using it for confidential, regulated, or personally sensitive topics unless you can disable memory access and confirm exactly what queries will be sent externally.

A.I.G

Vulnerability Patterns

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

Findings (2)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:430
Finding: Unnecessary Access to Persistent Agent Memory
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: README.md:14
Finding: Misleading Offline Claim Despite Mandatory Network Operations
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The README explicitly advertises broad natural-language triggers such as asking for "deep research on..." or "exhaustive analysis of...", which can cause the skill to activate on generic user phrasing rather than an intentional, namespaced command. In an agent environment with multiple skills, this increases the risk of unintended invocation, routing sensitive or unrelated requests into this workflow and causing unnecessary web access, data exposure to external sites, or user confusion about which capability is acting.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger guidance includes the phrase "Tell me everything about X," which is broad and overlaps with normal conversational requests. In systems that auto-invoke skills based on natural language, this can cause unintended activation of a high-autonomy research workflow, leading to unnecessary external tool use, excessive data retrieval, or execution of a more powerful workflow than the user intended.
Content: No source excerpt is available for this finding.

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 91% confidence
Finding: The workflow explicitly labels Phase 3 as "Auto-Execute," indicating the skill may proceed with multiple research tool calls without an additional user approval step at that stage. In a research skill that uses web_search and web_fetch extensively, this increases the risk of unintended autonomous actions, excessive external data retrieval, and processing of sensitive or regulated topics without a fresh checkpoint.
Content: Scanner excerpt · example.md (reported line 76)May include surrounding context.
md
--- ## Phase 3: Research Cycles (Auto-Execute) ### Theme 1: Market Landscape — Cycle 1

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation guidance includes broad natural-language triggers like mentioning "deep research" or "exhaustive analysis," which can cause the skill to activate during ordinary conversation rather than through an explicit command. In a powerful research skill that can autonomously perform multi-phase tool use, this increases the chance of unintended execution, scope creep, and accidental external data access.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.