Back to skill

Security audit

research-logger

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but its shell script unsafely mixes user and web-fetched text into sed commands, creating a credible local command-execution risk.

Review this skill before installing. It is purpose-aligned, but do not use it with confidential topics or untrusted research targets unless the template fill is fixed to treat all replacement values as literal data instead of sed syntax, ideally with a safer templating implementation and a preview or no-save mode.

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

Error
Location
research_logger.sh:90
Finding

Arbitrary sed Program Injection Through Unescaped Template Values

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script sends the user-supplied topic directly to external helpers (web_search, web_fetch, and gifgrep) without any notice, consent, or sensitivity check. This can leak confidential research subjects, internal project names, or personal data to third-party services, and the skill’s purpose explicitly encourages such transmission, making the privacy risk real rather than hypothetical.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises research, GIF matching, and note creation, but does not clearly warn users that fetched web content and generated notes will be automatically persisted into Bear. This can cause users to unknowingly save untrusted, sensitive, or irrelevant content into a long-lived notes store, increasing the risk of privacy leakage, accidental retention, and downstream trust in AI-generated notes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The script creates a Bear note and, on failure, writes a markdown file locally without clearly informing the user in advance that their query, fetched content, and generated notes will be persisted. While this is consistent with the tool’s stated purpose, it still creates an undisclosed data-retention risk if the topic or collected content is sensitive.

Content

No source excerpt is available for this finding.