Back to skill

Security audit

job-posting-comparison

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for comparing job postings, but it also exposes a broad public web-scraping route that is not clearly constrained to job sources.

Install only if you are comfortable giving the skill access to your Crawlora API key and allowing it to send job queries, posting IDs, and requested URLs to Crawlora. Review use of /web/scrape carefully, since it can scrape arbitrary public URLs and is not limited to job-posting domains by the artifact.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (13)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill explicitly instructs use of a shell script but does not declare any tool scope or allowed-tools constraints. That creates an overbroad execution surface where an agent may invoke shell capability without policy-level restriction, increasing the chance of unintended command execution or misuse if the skill or surrounding workflow is modified or composed with untrusted input.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is scoped to comparing job postings across Crawlora jobs datasets, ATS boards, and Indeed, but the endpoint list also exposes a general-purpose arbitrary URL scraping capability. That expands the tool's authority beyond the declared purpose and can enable unintended data exfiltration, scraping of unrelated sites, or operator misuse by fetching attacker-chosen URLs.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Allowing arbitrary URL scraping is context-inappropriate for a narrowly scoped job-posting comparison skill because it lets prompts or downstream logic pivot into unrelated web retrieval. In an agent setting, this broadens the attack surface and increases the chance of prompt-driven misuse, collection of untrusted content, or access to domains outside the expected data providers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/crawlora.sh (reported line 2)May include surrounding context.

sh
#!/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.
#

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
#!/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:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · reference/endpoints.md (reported line 7)May include surrounding context.

md
#!/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:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/crawlora.sh (reported line 3)May include surrounding context.

sh
#!/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:

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/crawlora.sh (reported line 24)May include surrounding context.

sh
#!/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:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The helper explicitly permits POST /web/scrape, which is a generic scraping capability broader than the job-posting comparison purpose described in the skill metadata. In an agent setting, this expands the external access surface and could be abused to fetch arbitrary third-party pages or process untrusted targets outside the intended job-source catalog.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/crawlora.sh (reported line 180)May include surrounding context.

sh
# config supplies the header and is removed automatically on exit.
umask 077
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")

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/crawlora.sh (reported line 206)May include surrounding context.

sh
[ -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 -q -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" --data-binary @- "${base}${path}"
fi

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This markdown file instructs users to supply x-api-key: $CRAWLORA_API_KEY, which involves access to sensitive credentials. The document does not include any caution about protecting the key, avoiding accidental logging/sharing, or ensuring it is sourced securely.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file header and usage examples present the script as a general helper for arbitrary Crawlora endpoints, including unrelated examples like Amazon, YouTube, Google Search, and Google Trends. The implemented logic later rejects anything outside a specific job-posting-comparison route allowlist, so the documentation actively misstates what the script actually does.

Content

No source excerpt is available for this finding.