ClawHub
Back to skill

Security audit

directory-submissions

Security checks for vulnerabilities and agentic risk

Overview

This skill gives disclosed marketing guidance for directory submissions and backlink tracking, with no hidden execution, persistence, or credential handling found.

Install only if you want hands-on marketing guidance for public listings, launch sites, review platforms, and backlink tracking. Keep submissions relevant, avoid spammy venues, do not share private customer data in public listings, and review each platform's rules before posting or asking users for reviews.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/directory-list.md (reported line 477)May include surrounding context.

md
2. **curl:** `curl -sIL https://directory.com/your-listing | grep -i link`
3. **SEO tools:** Ahrefs Site Explorer → Backlinks → filter by this directory's domain.

**Re-verify quarterly.** Directories sometimes change all outbound links to nofollow without warning — if DR stops moving, check whether your biggest inbound links have silently flipped.

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 · references/submission-tracker-template.csv (reported line 75)May include surrounding context.

text
NoCode.Tech,5,https://www.nocode.tech/submit,No-Code,35,Yes,,Draft,,,No-code,,,
Zapier App Directory,7,https://zapier.com/developer,Integration,91,Yes,,Draft,,,Integration,,,
HubSpot App Marketplace,7,https://ecosystem.hubspot.com/marketplace,Integration,93,Yes,,Draft,,,Integration,,,
Slack App Directory,7,https://api.slack.com/apps,Integration,89,Yes,,Draft,,,Integration,,,
Airtable Marketplace,7,https://airtable.com/marketplace,Integration,82,Yes,,Draft,,,Integration,,,
Notion Integrations,7,https://www.notion.so/integrations,Integration,88,Yes,,Draft,,,Integration,,,
Make (Integromat),7,https://www.make.com/en/partners,Integration,70,Yes,,Draft,,,Integration,,,

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The template materially exceeds the stated purpose of directory submissions and includes profile sites, forums, article farms, bookmarking sites, and local citation channels. In an agent skill, this broadens operator behavior into spammy or policy-violating off-platform promotion and raises the chance of mass account creation, reputational harm, and misuse of stored submission/account data.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file includes black-hat or weakly relevant promotional venues such as low-quality forums, article directories, and similar channels that are not justified by the skill's stated use case. This can steer an agent or user toward manipulative link-building practices, increasing the risk of platform abuse, search penalties, and reputational damage.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/directory-list.md (reported line 351)May include surrounding context.

md
PR Free,11,https://www.pr-free.com,Press release,62,Yes,,Draft,,,PR,,,
SubmissionWebDirectory,11,https://www.submissionwebdirectory.com,General,61,Yes,,Draft,,,Article,,,
Sooper Articles,11,https://www.sooperarticles.com,Article,60,Yes,,Draft,,,Article,,,
OnToplist,11,https://www.ontoplist.com,Blog directory,60,Yes,,Draft,,,Article,,,
BlogEngage,11,https://www.blogengage.com,Blog directory,55,Yes,,Draft,,,Article,,,
BizSugar,11,https://www.bizsugar.com,Business,55,Yes,,Draft,,,Article,,,
TechPluto,11,https://www.techpluto.com,Marketing,50,Yes,,Draft,,,Article,,,

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/submission-tracker-template.csv (reported line 231)May include surrounding context.

text
PR Free,11,https://www.pr-free.com,Press release,62,Yes,,Draft,,,PR,,,
SubmissionWebDirectory,11,https://www.submissionwebdirectory.com,General,61,Yes,,Draft,,,Article,,,
Sooper Articles,11,https://www.sooperarticles.com,Article,60,Yes,,Draft,,,Article,,,
OnToplist,11,https://www.ontoplist.com,Blog directory,60,Yes,,Draft,,,Article,,,
BlogEngage,11,https://www.blogengage.com,Blog directory,55,Yes,,Draft,,,Article,,,
BizSugar,11,https://www.bizsugar.com,Business,55,Yes,,Draft,,,Article,,,
TechPluto,11,https://www.techpluto.com,Marketing,50,Yes,,Draft,,,Article,,,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The expected output instructs the skill to say launches should occur at '12:01 AM Pacific Time on Tuesday/Wednesday/Thursday only.' This hard-codes a locale/timezone-specific requirement in natural language without offering user choice or explaining that the constraint is tied to a region-specific platform policy.

Content

No source excerpt is available for this finding.