Back to skill

Security audit

Industry Briefing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple briefing template that tells the agent to search public web sources and summarize recent industry news.

Install only if you are comfortable having the topics you ask about searched on the public web. Avoid using confidential company names, internal projects, or personal sensitive topics unless your agent's web-search provider and privacy settings are acceptable to you.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Confidence
65% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 205)May include surrounding context.

md
for Sickle Cell** (Nature Genetics, 1 day ago)
   - Long-term data from exa-cel trials shows sustained benefit with manageable side effects.

2. **Apple Health App Revolutionizes Chronic Disease Monitoring** (CNBC, 2 days ago)
   - Apple introduces proactive monitoring with AI-driven insulin sensitivity and heart health predictive analytics.

3. **FDA Approves First AI-Generated Drug Molecule** (FiercePharma, Today)
   - Sanofi's diabetes candidate becomes the first fully AI-designed drug to receive regulatory clearance.

## Key Trends
- **AI-Driven Clinical Trials**: Companies are using AI to reduce trial recruitment times by 40-50%, particularly for rare diseases.
- **Remote Patient Monitoring Market Grows**: Remote monitoring devices and wearables market expands 35% YoY as hospitals embrace continuous data.

## Companies to Watch
- **CRISPR Therapeutics**: Targets $1B+ in exa-cel sales by 2028 with expanded indications.
- **DeepMind/Isomorphic Labs**: Partner with GSK and Illumina

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs use of web_search and web_fetch against user-provided topics but does not warn that the queried topic may be sent to external search/fetch providers. This creates a privacy/transparency issue: sensitive company names, internal initiatives, or personal topics could be disclosed to third-party services without informed user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

Defaulting to English without explicit user opt-in can cause the skill to send or frame requests in a language the user did not choose, which may reduce accuracy and create fairness or preference mismatches. While not a direct security flaw, it is a genuine privacy/UX policy issue when defaults are applied to externally sourced content without confirming user intent.

Content

No source excerpt is available for this finding.