techsmith-upgrade-migration

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design as it ingests local configuration and diagnostic data.
  • Ingestion points: The skill instructions direct the agent to use Read, Glob, and Grep to inspect local scripts, manifests, logs, and tests for information regarding product versions and formats (SKILL.md).
  • Boundary markers: There are no defined delimiters or specific 'ignore' instructions applied to the content of these local files when they are read into the agent's context.
  • Capability inventory: The skill allows the use of Write, Edit, and WebFetch tools, which could potentially be manipulated by malicious instructions hidden in local log or manifest files (SKILL.md).
  • Sanitization: The skill provides clear instructions to redact keys and identifiers, but it does not specify sanitization or validation protocols for the structural or textual content parsed from local migration manifests.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:28 PM
Security Audit — agent-trust-hub — techsmith-upgrade-migration