ClawHub
Back to skill

Security audit

SEC Filing Scanner for M&A

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused SEC filing analysis guide that uses public SEC data sources and does not install code, persist, or request privileged access.

Before installing, be aware that company identifiers or search terms may be sent to SEC public data endpoints during use. The broad triggers may activate the skill in some generic annual or quarterly report contexts, but the reviewed artifact is otherwise limited to public SEC filing analysis.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest trigger list includes a single-word activation phrase, "edgar," without additional context or constraints. Because the file does not provide negative examples or scope limits, this could cause unintended invocation when users mention EDGAR in a general discussion rather than requesting SEC filing analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

"Annual report" is a common phrase that can refer to many contexts beyond SEC filing analysis, including internal company reports or general finance discussions. The skill does not narrow the trigger to SEC/EDGAR usage or provide exclusions, making accidental activation more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "quarterly report" is widely used in ordinary business and finance settings and is not specific to EDGAR or 10-Q analysis. Without contextual constraints or negative examples, the activation condition is ambiguous and may match unrelated requests.

Content

No source excerpt is available for this finding.

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 33)May include surrounding context.

md
## Data Source

SEC EDGAR API (free, no API key, 10 req/sec rate limit):
- Company Facts: `https://data.sec.gov/api/xbrl/companyfacts/CIK{cik}.json`
- Submissions: `https://data.sec.gov/submissions/CIK{cik}.json`
- Full-Text Search: `https://efts.sec.gov/LATEST/search-index?q=...`

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 34)May include surrounding context.

md
## Data Source

SEC EDGAR API (free, no API key, 10 req/sec rate limit):
- Company Facts: `https://data.sec.gov/api/xbrl/companyfacts/CIK{cik}.json`
- Submissions: `https://data.sec.gov/submissions/CIK{cik}.json`
- Full-Text Search: `https://efts.sec.gov/LATEST/search-index?q=...`

Static analysis

No suspicious patterns detected.