Skills
skills/netresearch/automated-assessment-skill/add-checkpoints/Gen Agent Trust Hub

add-checkpoints

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's workflow includes executing a local script scripts/run-checkpoints.sh for validation purposes.
  • [PROMPT_INJECTION]: The skill analyzes instructions from target SKILL.md files (Ingestion point) to generate configurations. It does not define explicit boundary markers for this data. The skill possesses the ability to write files and execute local validation scripts (Capability inventory). No specific sanitization or validation of the ingested content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 08:42 PM