Back to skill

Security audit

unusual-options-activity

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with medium confidence: the reported API request appears aligned with its stated market-activity purpose, though a scanner raised a concern about external fetching and the review is partial.

The verdict is benign, but it is not a guarantee of safety. Before installing, consider that the skill makes a request to an external service and check that you trust that service and are comfortable using it. The scanner review was partial because some referenced local paths were not matched to bundled files.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 131)May include surrounding context.

changes.

bash
curl -s -H "X-SentiSense-API-Key: $SENTISENSE_API_KEY" \
  "https://app.sentisense.ai/api/v1/options/overview"

Rows are pre-ranked by interestScore. Lead with the top few by that score, and show each one's notionalVol beside it: a scored row traded at least $100,000 of premium that session, so a stretched reading near that floor is still thin activity and should be labeled as such. Then re-sort client-side for a specific lens: notionalVol for "most active by premium", abs(ivMove20) for "biggest IV moves", or pcVolPctl1y for the most put-heavy names. Always report the percentile alongside the raw reading, and skip rows where interestScore is omitted (unscored: a building baseline or a session below the liquidity floor).