Security audit

Call Academic Search Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is a research workflow, but it tells the agent to treat its own instructions and external search results as unquestionable authority, which creates review-worthy prompt-injection and misinformation risk.

Review before installing. The skill can be useful for structured literature research, but users should narrow its activation language and remove claims that external sources or skill text outrank normal agent rules. Retrieved webpages and search results should be treated as evidence to verify, not instructions to obey.

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:13
Finding: Skill instructions override agent safety boundaries and require unconditional trust in external content
Content: View full analysis
Remediation: View remediation

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 skill description is extremely broad and vague ('AI agent for call academic search agent tasks'), which can cause unintended activation for loosely related prompts and route users into a powerful research workflow without clear scope boundaries. In this skill, that risk is amplified because the body grants strong authority to external tool output and prescribes file creation/submission behavior, so ambiguous invocation increases the chance of unnecessary tool use, data handling, and prompt-driven misuse.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.