draft

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the date command to generate formatted timestamps for draft metadata in SKILL.md. This is a standard, benign use of system utilities.
  • [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it aggregates data from various sources to generate content. However, the risk is minimal given the skill's purpose for drafting text for user review.
  • Ingestion points: User-supplied topics and recipients in SKILL.md; context gathered from oracle_search(), /fyi logs, and session retrospectives.
  • Boundary markers: Absent; the templates do not use specific delimiters to isolate external context from instructions.
  • Capability inventory: The skill writes generated text files to the local ψ/writing/drafts/ directory.
  • Sanitization: No explicit sanitization or escaping of external data is defined before it is interpolated into the drafting templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 06:41 PM