ClawHub
Back to skill

Security audit

Faers Multi Drug Soc Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a planning-only FAERS pharmacovigilance skill with no executable code, persistence, credential use, or hidden side effects.

Before installing, treat this as a research-design aid, not medical advice or proof of causality. Review generated plans for comparator suitability, data-quality assumptions, and appropriate FAERS limitations, especially because pharmacovigilance disproportionality can be misinterpreted as incidence or causal risk.

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 236)May include surrounding context.

md
*If the user requests an all-SOC sweep or pan-MedDRA signal scan:*
> "This skill is designed for single-SOC comparative pharmacovigilance designs. An all-SOC disproportionality sweep is a different study type outside this scope. I can help you: (a) identify the highest-priority SOC for your drug and design a focused study there, or (b) describe how an all-SOC PRR/EBGM screen would differ methodologically. Which would be more useful?"

*If the user asks to frame FAERS disproportionality results as causal evidence without caveats:*
> "FAERS disproportionality analysis (ROR/PRR) cannot establish causality — it quantifies reporting proportion differences, not incidence or risk. This skill will always include appropriate epistemic caveats. I can design the strongest possible comparative pharmacovigilance study with active-comparator restriction and sensitivity analysis to maximize the evidentiary weight of the findings."

*If the request is unrelated to FAERS/pharmacovigilance study design:*

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger text is overly broad and includes catch-all language such as 'or any phrasing like' plus 'Always use this skill', which can cause the skill to be invoked outside narrowly intended contexts. In an agentic environment, over-triggering can route unrelated or only loosely related user requests into this planner, leading to inappropriate tool selection, reduced reliability, and possible bypass of safer or more suitable workflows.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This JSON manifest-like report states that "Trigger precision" is excellent, but it does not actually enumerate the trigger phrases, activation conditions, or exclusion boundaries in the file itself. For manifest-scope review under SQP-1, the absence of concrete trigger definitions can make invocation scope unverifiable and potentially ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.