Back to skill

Security audit

agent-bom compliance

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no executable files and two purpose-related findings; the main caveat is that its documented SBOM command writes an output file despite the manifest declaring no file writes.

The verdict is benign with high confidence, and the listed component was fully scanned. Before installing, consider that generating an SBOM may create a file even though the manifest declares no file writes; choose where that output should go and avoid overwriting an existing file unintentionally.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
env: []
      credentials: none
    credential_policy: "Zero credentials required for OWASP/NIST/EU AI Act compliance and SBOM generation. CIS benchmark checks (AWS, Azure, GCP, Snowflake) optionally accept cloud credentials — only used locally to call cloud APIs, never transmitted elsewhere."
    credential_handling: "Use only operator-configured cloud SDK credentials for explicitly requested CIS checks. Do not ask users to paste secrets, and never print cloud tokens, private keys, passwords, or connection strings."
    optional_env:
      - name: AWS_PROFILE
        purpose: "AWS CIS benchmark checks — uses boto3 with your local AWS profile"

The documented SBOM command writes a file despite the manifest declaring no file writes.

Low
Category
Excessive Agency
Confidence
97% confidence
Finding

The manifest declares file_writes: [], but the documented command uses -o sbom.json to write an output file. This understates the skill's filesystem effects and could mislead operators or permission systems relying on the declaration; however, the write is explicit, relevant to SBOM generation, and shows no evidence of malicious targeting.

Content

No source excerpt is available for this finding.