skills/aktsmm/agent-skills/fact-check/Gen Agent Trust Hub

fact-check

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (files, selection, pasted text, and URLs) and utilizes capabilities like workspace file access and command execution to verify claims.
  • Ingestion points: Processes files, selection, pasted text, and URL lists provided by the user (SKILL.md).
  • Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore potential instructions embedded within the content being fact-checked.
  • Capability inventory: Accesses workspace files using tools like Test-Path and Get-ChildItem, performs network fetches for verification against official documentation, and executes informational commands such as Get-Command and --version (SKILL.md).
  • Sanitization: The skill lacks instructions for sanitizing or escaping the external content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:17 AM