ClawHub
Back to skill

Security audit

fiverr-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a Fiverr research helper, but its bundled API script is a broad Crawlora client that can call non-Fiverr paths and send arbitrary POST bodies with the user's API key.

Review before installing. Use it only if you are comfortable giving the skill a Crawlora API key and letting its helper make outbound requests. Prefer a version whose script restricts calls to the documented /fiverr/search, /fiverr/gig/{username}/{slug}, and /fiverr/seller/{username} GET endpoints and does not allow arbitrary base URLs or POST bodies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Confidence
97% confidence
Finding
The helper is documented and implemented as a generic Crawlora client that can call arbitrary API paths, not just Fiverr-specific endpoints. In the context of a skill advertised as Fiverr-only research, this creates a capability mismatch that could let the agent access unrelated external data sources and perform broader network-backed research than users or reviewers expect.

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The core logic accepts arbitrary paths, query parameters, HTTP methods, and POST bodies, making it a general-purpose external research client rather than a constrained Fiverr lookup tool. That overbroad capability increases the chance of misuse, data exfiltration to third-party services reachable through Crawlora, or policy bypass through undocumented endpoints.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -fsS -G "${auth[@]}" "${qs[@]}" "${base}${path}"
else
  [ -n "$body" ] || body="${rest[0]:-{}}"
  curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" -d "$body" "${base}${path}"
fi
Confidence
92% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

External Transmission

Medium
Category
Data Exfiltration
Content
set -euo pipefail

: "${CRAWLORA_API_KEY:?Set CRAWLORA_API_KEY first — get a free key at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills}"
base="${CRAWLORA_API_BASE:-https://api.crawlora.net/api/v1}"

method="GET"
body=""
Confidence
74% confidence
Finding
https://api.crawlora.net/

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:25