nuclei-scan

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external target URLs and local template files using command-line tools. An attacker could potentially embed malicious instructions in target responses or local templates that the agent processes.
  • Ingestion points: User-supplied target URLs and local files in ~/nuclei-templates/ (documented in SKILL.md).
  • Boundary markers: No delimiters or explicit warnings to ignore instructions embedded in target data are present.
  • Capability inventory: The skill utilizes nuclei, curl, find, grep, and cat for network and file operations (documented in SKILL.md).
  • Sanitization: There is no mention of input validation or sanitization for target URLs or template content before they are used in shell commands.
  • [COMMAND_EXECUTION]: The skill frequently uses shell commands to perform its core functions. While these are documented as standard usage for the tool, the reliance on shell execution creates a risk if parameters are not properly escaped.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:53 PM
Security Audit — agent-trust-hub — nuclei-scan