skills/verstak-ai/skills/writing/Gen Agent Trust Hub

writing

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation and modification of nodes within a shared graph database, which serves as a persistent context for multiple agents.
  • Ingestion points: The skill uses user-provided names, descriptions, and other metadata fields from SKILL.md to populate graph nodes through tools like nks_add_kriya and nks_add_phenomenon.
  • Boundary markers: There are no explicit instructions in SKILL.md for the agent to sanitize or enclose user-provided text in delimiters when writing to the graph.
  • Capability inventory: The skill utilizes a suite of tools listed in SKILL.md, such as nks_add_*, nks_update, nks_arrow, and nks_batch, to commit data to the shared environment.
  • Sanitization: The instructions in SKILL.md do not specify any validation or filtering of user input before it is written to the graph database.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:06 PM
Security Audit — agent-trust-hub — writing