Back to skill

Security audit

job-market-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Crawlora API wrapper for job and freelance market research, with expected external requests and no evidence of hidden persistence, privilege escalation, or destructive behavior.

Install only if you are comfortable sending job, company, freelancer, and marketplace search terms to Crawlora using your Crawlora API key. Avoid sending secrets, confidential internal plans, private candidate data, or sensitive company research terms unless that third-party use is acceptable to you.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs use of a shell helper (`scripts/crawlora.sh`) and therefore has code-execution capability, but it does not declare any tool scope, permissions, or allowed-tools constraints. That creates an overbroad execution surface where an agent may invoke shell access without explicit policy boundaries, increasing the risk of unintended command execution or misuse of local environment data.

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
79% confidence
Finding
The skill sends data and an API credential to an external third-party service (`api.crawlora.net`), which is an external transmission boundary. While this is core to the skill's purpose and the file warns not to hardcode or expose the key, using a shell-based helper plus environment-resident secrets still creates a real risk of unreviewed data egress or accidental disclosure if prompts, queries, or local context are passed through unsafely.

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.

**57 endpoints across 10 platform group(s).**
Confidence
91% confidence
Finding
The file confirms that the skill transmits user-supplied query parameters to an external service at `api.crawlora.net` using an authenticated API key. In the context of a research skill, outbound transmission is expected, but it still creates a real data-exposure boundary: sensitive search terms, company names, or identifiers entered by users may leave the local trust boundary and be logged or retained by the third-party provider.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
This markdown file instructs callers to use the `x-api-key: $CRAWLORA_API_KEY` header for remote API access, which implies both use of sensitive credentials and transmission of user-supplied queries to an external service. The endpoint reference does not include any warning about handling the API key securely or that requests send data off-system to Crawlora.

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.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The iCIMS job endpoint description states that `lang` defaults to `en-us`, which imposes a specific locale choice in the skill documentation. The file does not indicate user choice, opt-in, or a justification for this default locale behavior.

Static analysis

No suspicious patterns detected.