techsmith-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and samples from official TechSmith domains (assets.techsmith.com, support.techsmith.com) and their official GitHub organization (github.com/TechSmith). These are well-known, trusted sources for the specific product being automated, and the references are handled neutrally.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes repository files via Read, Glob, and Grep to identify COM automation patterns.
  • Ingestion points: Reads local scripts and manifests as specified in the Instructions section.
  • Boundary markers: The instructions explicitly define "Approval Boundaries" and require following repository conventions.
  • Capability inventory: The skill uses Write and Edit to implement adapters and migrate code, and interacts with the local COM system (Snagit.ImageCapture.1).
  • Sanitization: The skill mandates "path-safe results", "redaction of all keys and activation artifacts", and "artifact-validation failure" for invalid paths, effectively mitigating injection risks during data processing.
  • [CREDENTIALS_UNSAFE]: The skill proactively addresses credential safety by instructing the agent to redact all keys, account identifiers, and activation artifacts during execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:30 PM
Security Audit — agent-trust-hub — techsmith-sdk-patterns