Back to skill

Security audit

anime-manga-research

Security checks across malware telemetry and agentic risk

Overview

The skill discloses its anime/manga API use, but its helper script is broader than advertised and can send authenticated requests outside that purpose.

Review before installing. Use only if you are comfortable sending anime/manga searches and IDs to Crawlora, keep CRAWLORA_API_KEY private, and avoid sensitive query terms. The publisher should scope the helper to the documented GET /anime and /manga endpoints and prevent accidental key transmission to alternate API bases.

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 (6)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The helper and its documented usage are not constrained to anime/manga endpoints despite the skill being advertised for anime/manga research only. This creates unnecessary capability breadth: an agent using this script can access unrelated Crawlora API domains, increasing the chance of policy bypass, data exfiltration, or off-scope web retrieval through a trusted skill wrapper.

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script accepts arbitrary HTTP methods and arbitrary API paths, effectively exposing a general-purpose authenticated API client rather than a narrowly scoped anime/manga research tool. In an agent environment, this broadens the attack surface significantly because prompt-influenced inputs can steer the tool to unintended Crawlora capabilities using the caller's API key.

Intent-Code Divergence

Low
Confidence
87% confidence
Finding
The comments advertise generic search, transcript, and trends operations that contradict the declared anime/manga-only purpose of the skill. While comments alone do not execute, they signal intended off-scope use and can encourage integrators or agent authors to expose broader functionality than users expect.

External Transmission

Medium
Category
Data Exfiltration
Content
Endpoints this skill uses, grouped by platform. Call them via `scripts/crawlora.sh` (see SKILL.md).

All paths are relative to the API base `https://api.crawlora.net/api/v1` and require the header `x-api-key: $CRAWLORA_API_KEY`. Path params like `{id}` are substituted into the URL; `GET` params go in the query string; `POST` params go in a JSON body.

**12 endpoints across 2 platform group(s).**
Confidence
83% confidence
Finding
https://api.crawlora.net/

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}${path}"
fi
Confidence
84% confidence
Finding
curl -fsS -X "$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
81% 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:23