vulnerability-scanner

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Prompt Injection (LOW): The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: External file content accessed via Read, Glob, and Grep tools.
  • Boundary markers: Absent; there are no instructions or delimiters provided to prevent the agent from following instructions embedded within the files it scans.
  • Capability inventory: The skill utilizes Bash and executes a local Python script.
  • Sanitization: Absent; content from target files is ingested directly into the prompt context.
  • Command Execution (LOW): The skill requests access to Bash and instructs the agent to execute a local Python script (scripts/security_scan.py). While these capabilities are consistent with the skill's primary purpose as a vulnerability scanner, they represent a potential risk if the agent processes malicious instructions from a scanned project.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:59 PM