Back to skill

Security audit

sports-scores-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned sports data helper that sends user-directed sports queries to Crawlora, with one documentation gap around extra Cricinfo endpoints.

Before installing, be comfortable sending sports queries, URLs, and identifiers to Crawlora under your Crawlora API key. Do not pass private or sensitive data as parameters, and note that the skill includes Cricinfo endpoints even though the main description does not call them out.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs use of a shell helper script but does not declare any tool restrictions or allowed-tools scope. That creates unnecessary execution latitude: an agent/runtime may permit broader shell usage than is required, increasing the chance of command execution misuse or abuse if future edits, prompt injection, or parameter interpolation reach the shell layer.

External Transmission

Medium
Category
Data Exfiltration
Content
- Get a free Crawlora API key (2,000 credits/mo, no card) at [https://crawlora.net](https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills).
- Set `CRAWLORA_API_KEY` in the environment before running the helper.
- The helper reads `CRAWLORA_API_KEY` from the environment and sends requests to `https://api.crawlora.net/api/v1`. Missing/invalid key → `401`.

## How it works
Confidence
80% confidence
Finding
The skill sends requests and an API credential to an external third-party service, which is an external transmission boundary and can expose user queries, metadata, and usage patterns outside the local environment. In context this is expected functionality, but it still carries data-handling and supply-chain risk because the skill depends on Crawlora for live data and instructs storing a reusable secret in the environment.

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.

**74 endpoints across 6 platform group(s).**
Confidence
91% confidence
Finding
The skill is explicitly designed to send data to an external service at `https://api.crawlora.net/api/v1`, so external transmission is real, not hypothetical. In context this is expected behavior for a data-retrieval skill, but it still creates a security boundary where user queries, identifiers, URLs, and associated metadata leave the local system and depend on the security and handling practices of a third party.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The endpoint reference exposes substantial Cricinfo functionality that is not disclosed in the skill's stated description, which claims coverage of ESPN, SofaScore, MLB, Strava, and DraftKings only. This kind of capability drift weakens user consent and reviewer understanding, making it easier for the skill to access additional external content sources beyond what operators or users expect.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
# Keep the API key out of the curl process command line. A private temporary
# config supplies the header and is removed automatically on exit.
curl_config="$(mktemp "${TMPDIR:-/tmp}/crawlora-curl.XXXXXX")"
chmod 600 "$curl_config"
trap 'rm -f "$curl_config"' EXIT
printf 'header = "x-api-key: %s"\n' "$CRAWLORA_API_KEY" >"$curl_config"
auth=(--config "$curl_config")
Confidence
80% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

External Transmission

Medium
Category
Data Exfiltration
Content
[ -n "$body" ] || body='{}'
  # Stream the body on stdin so curl never interprets a user value as its
  # @file shorthand (and cannot read local files supplied in a request body).
  printf '%s' "$body" | curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" --data-binary @- "${base}${path}"
fi
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The file states that requests require an `x-api-key` for a third-party service but does not include a user warning or trust notice about sending requests through Crawlora. Even if the key itself is not user-supplied, the omission reduces transparency around third-party processing and can mislead users about where their queries and selected parameters are being transmitted.

Static analysis

No suspicious patterns detected.