summarize

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local file system which presents a surface for indirect prompt injection.
  • Ingestion points: Content is ingested from local files matching a user-specified scope (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are instructed for use when processing the file content.
  • Capability inventory: The skill allows the agent to read local files and write results to the file system (SKILL.md).
  • Sanitization: The instructions do not include steps for sanitizing or validating the content of the files before summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 09:03 PM
Security Audit — agent-trust-hub — summarize