Security checks for vulnerabilities and agentic risk
Overview
ClawScan rates this skill suspicious because it reports a PostgreSQL configuration exposed on all host interfaces with fixed superuser credentials, alongside installation and workflow risks.
Consider the reported database exposure a serious installation concern. Before installing, review the PostgreSQL configuration and the unpinned installation commands, and check how the host runtime limits the skill's access. Scanner coverage is incomplete: although all listed components were scanned, some references could not be resolved.
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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)
T09 · Insecure Skill Coding Practices
Warning
Location
assets/docker-compose.fullstack.yaml:5
Finding
PostgreSQL is published on all host interfaces with fixed superuser credentials
Content
View full analysis
Impact
A reachable attacker can read, modify, or delete database contents and administer database roles. The persistent pgdata volume retains application data exposed through this configuration.
The visual-browser workflow omits a warning that page screenshots and task prompts may be transmitted to the configured model provider.
High
Category
Output Handling
Confidence
97% confidence
Finding
The workflow combines provider-backed visual inference with access to authenticated browser pages without explaining that screenshots and prompts may leave the machine. This can disclose private page contents or credentials to the configured provider, even when the browser actions themselves are authorized.
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 · AGENTS.md (reported line 13)May include surrounding context.
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 · AGENTS.md (reported line 13)May include surrounding context.
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 55)May include surrounding context.
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 55)May include surrounding context.
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 · references/backend-playbook.md (reported line 175)May include surrounding context.
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 · references/nextjs-app-router-playbook.md (reported line 147)May include surrounding context.
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 · skills/api-design/SKILL.md (reported line 7)May include surrounding context.
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 · AGENTS.md (reported line 14)May include surrounding context.
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 · AGENTS.md (reported line 14)May include surrounding context.
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 56)May include surrounding context.
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 56)May include surrounding context.
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 · references/backend-playbook.md (reported line 175)May include surrounding context.
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 · skills/backend-patterns/SKILL.md (reported line 7)May include surrounding context.
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 · AGENTS.md (reported line 15)May include surrounding context.
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 · AGENTS.md (reported line 15)May include surrounding context.
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 57)May include surrounding context.
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 57)May include surrounding context.
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 · references/backend-playbook.md (reported line 175)May include surrounding context.
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 · skills/database-design/SKILL.md (reported line 7)May include surrounding context.
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 · AGENTS.md (reported line 16)May include surrounding context.
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 · AGENTS.md (reported line 16)May include surrounding context.
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 58)May include surrounding context.
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 58)May include surrounding context.
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 · references/backend-playbook.md (reported line 175)May include surrounding context.