ClawHub
Back to skill

Security audit

deep-research-pro

Security checks for vulnerabilities and agentic risk

Overview

The research workflow is mostly coherent, but the install and CLI documentation points users toward unaudited external code from an inconsistent source.

Review the install source before using this skill. The core SkillBoss search workflow is understandable, but do not run the advertised scripts/research CLI unless you verify which GitHub repository is authoritative and inspect the script contents. Avoid sending secrets, internal URLs, or sensitive investigations as research queries unless you trust SkillBoss API Hub's handling of that data.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:25
Finding

Inconsistent and Unpinned Installation Source Exposes Users to Unaudited Code

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (17)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README advertises web search and scraping through SkillBoss API Hub but does not warn that user queries and target URLs are transmitted to a third-party service. In a research skill, prompts may contain sensitive business, personal, or investigative data, so undisclosed external transmission creates a meaningful privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction says to use this workflow 'when the user asks for research on any topic,' which is extremely broad and overlaps with common user requests. The file does not define clearer trigger boundaries, exclusions, or negative examples to distinguish when this skill should activate versus a normal answer flow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The phrase 'just research it' is a generic everyday instruction and could match many ambiguous situations. Without additional scope constraints, it increases the risk of unintended invocation of this deep-research workflow.

Content

No source excerpt is available for this finding.

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 46)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

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 55)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

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 75)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

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 · SKILL.md (reported line 46)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

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 · SKILL.md (reported line 55)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

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 · SKILL.md (reported line 75)May include surrounding context.

md
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 47)May include surrounding context.

md
# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},
    timeout=60

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 56)May include surrounding context.

md
# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},
    timeout=60

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 76)May include surrounding context.

md
# Web search
result = requests.post(
    "https://api.heybossai.com/v1/pilot",
    headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
    json={"type": "search", "inputs": {"query": "<sub-question keywords>"}, "prefer": "balanced"},
    timeout=60

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs automatic creation of local files under a home-directory path without warning or obtaining user consent. Unexpected persistence can expose sensitive researched topics, clutter the filesystem, or create opportunities for abuse if the path or slug is influenced by untrusted input.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 158)May include surrounding context.

text
sessions_spawn(
  task: "Run deep research on [TOPIC]. Follow the deep-research-pro SKILL.md workflow.
  Read /home/clawdbot/clawd/skills/deep-research-pro/SKILL.md first.
  Goal: [user's goal]
  Specific angles: [any specifics]
  Save report to ~/clawd/research/[slug]/report.md

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file advertises that the skill can save output to files, which affects local user data, but it does not include any warning or caution about file creation or possible overwrites. Under the markdown-specific SQP-2 criteria, user-facing documentation should disclose behaviors that can affect data or system state.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description limits the skill to searching, synthesizing, and delivering cited reports. The documented workflow additionally includes creating directories and writing a report under ~/clawd/research/[slug], which is a persistence behavior not mentioned in the manifest description.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

A deep research agent obviously needs network access to search and scrape sources, but writing to ~/clawd/research is an extra capability beyond researching and delivering results in chat. The manifest does not state that the skill persists outputs locally, so this capability is not clearly justified from the declared purpose alone.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.