techsmith-ci-integration

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides instructions for secure CI/CD integration of desktop automation tools, focusing on portable checks and protecting licensed environments.\n- [EXTERNAL_DOWNLOADS]: The skill references official TechSmith documentation and samples from techsmith.com and github.com/TechSmith. These are well-known and authoritative sources for the products mentioned.\n- [INDIRECT_PROMPT_INJECTION]: The skill acknowledges the risk of processing external repository data and provides mitigation strategies.\n
  • Ingestion points: The skill processes repository assets (PowerShell scripts, C# code, manifests) via the repository-path argument as defined in SKILL.md.\n
  • Boundary markers: Explicitly defined in the Approval Boundaries and Tool Discipline sections of SKILL.md, including restrictions on software key placement and unapproved runner usage.\n
  • Capability inventory: The skill uses Read, Glob, Grep, WebFetch, Write, and Edit tools to inspect and modify repository content (SKILL.md).\n
  • Sanitization: Instructions mandate the redaction of keys, account identifiers, and activation artifacts, and require the removal of temporary artifacts after execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:29 PM
Security Audit — agent-trust-hub — techsmith-ci-integration