techsmith-security-basics

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of local scripts, manifests, and logs using file inspection tools, which introduces a potential surface for instructions embedded in analyzed files to influence the agent's behavior.
  • Ingestion points: The skill uses Read, Glob, and Grep to ingest data from local project files and logs (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions" wrappers are defined for processed files, though high-level security instructions are provided to the agent.
  • Capability inventory: The agent has the ability to use Write and Edit for file modification and WebFetch for network operations.
  • Sanitization: The instructions explicitly require the agent to redact keys, account identifiers, and activation artifacts before providing output.
  • [SAFE]: The skill directs the agent to utilize official documentation and deployment guides from well-known TechSmith domains and verified GitHub repositories for configuration and automation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:28 PM
Security Audit — agent-trust-hub — techsmith-security-basics