techsmith-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute PowerShell commands, such as New-Object -ComObject 'Snagit.ImageCapture.1', to interact with the local Snagit COM server for installation verification.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data which represents a potential injection surface if malicious content is provided in the arguments.
  • Ingestion points: User-provided workstation-alias and optional-output-directory arguments defined in SKILL.md frontmatter.
  • Boundary markers: Absent. The instructions do not use specific delimiters or warnings to ignore instructions embedded within the user arguments.
  • Capability inventory: The skill uses Write and Edit tools for file modification and executes shell-based COM automation via PowerShell.
  • Sanitization: Absent. There is no explicit validation or escaping of the input arguments before they are used in reports or command structures.
  • [EXTERNAL_DOWNLOADS]: The skill and its referenced documentation (references/official-docs.md) contain links to TechSmith's official asset domains (assets.techsmith.com), support portal (support.techsmith.com), and public GitHub repository (github.com/TechSmith/Snagit-COM-Samples). TechSmith is a well-known technology company.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:28 PM
Security Audit — agent-trust-hub — techsmith-hello-world