ClawHub
Back to skill

Security audit

Specter CLI – AI powered startup and deal sourcing

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for using Specter, but it asks users to install and run unreviewed external CLI code and documents sensitive/destructive operations without enough safeguards.

Review the upstream tryspecter-cli repository before installing, prefer a pinned commit or signed release, and avoid installing in an environment with unrelated secrets. Use the skill only with data you are allowed to send to Specter, store the API key carefully, avoid inline --api-key values, and manually confirm any delete command before running it.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:8
Finding

Execution of Unpinned Third-Party Code and Dependencies

Content
View full analysis
Remediation
View remediation

SkillSpector

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
87% confidence
Finding

The documented people enrichment, email resolution, and reverse email lookup commands send personal identifiers to an external intelligence platform but do not warn about privacy, consent, or compliance considerations. This is risky because users may process personal data without recognizing that the action transmits and enriches sensitive third-party information via an external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill exposes destructive commands to delete company lists, people lists, and saved searches without any warning, confirmation guidance, or indication of reversibility. In an agent-assisted workflow, this increases the risk of accidental destructive actions against production data, especially if a model or user invokes commands from documentation without fully understanding side effects.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

The skill explicitly documents external API calls that transmit company and person lookup data, along with use of an API key in requests. While external transmission is the expected function of this skill, it still represents a genuine security-relevant behavior because users may send sensitive business or personal data off-system and incur account or data exposure risks if this is not clearly disclosed and controlled.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

Enrich a company by domain:

bash
curl -X POST https://app.tryspecter.com/api/v1/companies/enrich \
  -H "X-API-KEY: $SPECTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain": "example.com"}'

Static analysis

No suspicious patterns detected.