Back to skill

Security audit

Academic Search.Bak

Security checks for vulnerabilities and agentic risk

Overview

This academic-search skill is mostly purpose-aligned, but its very broad triggers and plaintext arXiv endpoint create avoidable review-worthy risk.

Review the trigger list before installing, especially if your agent auto-activates skills from fuzzy matches. Use the skill only for intentional scholarly literature searches, avoid putting confidential research topics into broad prompts, and prefer an updated version that uses HTTPS-only arXiv endpoints and narrower academic-specific triggers.

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
knowledge/domain.md:15
Finding

Academic Search Requests Use an Unencrypted arXiv API Endpoint

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (12)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
84% confidence
Finding

The trigger phrase "find papers" begins with a built-in command verb and can shadow or conflict with generic "find" behavior in systems that use prefix or fuzzy trigger matching. This creates command-routing ambiguity that may let this skill intercept requests unexpectedly, especially when a user intends a general search rather than explicit academic workflow execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes highly generic terms such as "research" that are common in normal conversation and can cause the skill to activate outside a clearly academic-search context. Overbroad activation increases the chance of unintended tool use, response hijacking, or routing a user into this skill when another skill or default behavior would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Triggers like "cite" and "citation" are broad and overlap with many ordinary requests, including non-academic formatting or general writing assistance. This can lead to accidental invocation of the skill and unintended dependence on its external-search workflow, which widens attack surface and may disrupt correct command routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation rule fires on broad concepts like paper search, literature review, or research discovery without defining exclusions or minimum specificity. Because those intents frequently appear in mixed-purpose user requests, the skill may activate too aggressively, causing unintended external searches and overshadowing more suitable skills or built-in behaviors.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · knowledge/anti-patterns.md (reported line 73)May include surrounding context.

md
- **Fix**: Only return papers actually retrieved from database API responses. If the search returns fewer than 5 relevant results, report that honestly rather than padding with fabricated entries. Include the database query used so the user can verify.

### 15. Ignoring Open Access Status
- **Problem**: Returning papers behind paywalls without checking for open-access alternatives. Users without institutional access cannot read the papers.
- **Fix**: For each paper, check: (a) arXiv preprint version, (b) Semantic Scholar `openAccessPdf` field, (c) author's personal website or institutional repository. Flag papers with no open-access version available and suggest the user check their institutional library access.

## Workflow Anti-Patterns

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 95)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 109)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 113)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 114)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 123)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · knowledge/domain.md (reported line 124)May include surrounding context.

md
### API Endpoints

#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key

| Parameter | Description | Example |

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list contains very broad terms such as "research," "scholar," "cite," and "citation," which are likely to match many unrelated user requests and cause the skill to activate unexpectedly. In an agent environment, overbroad activation can route prompts into external search and synthesis behavior when the user did not intend it, increasing the chance of unnecessary data exposure, confusing tool use, or prompt-scope expansion.

Content

No source excerpt is available for this finding.