ghost-writer

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is instructed to ingest and follow directives found in external 'Voice DNA Documents'.
  • Ingestion points: 'Voice DNA Documents' provided by the user or external skills, as described in the intake phase of SKILL.md.
  • Boundary markers: Absent; there are no defined delimiters or instructions for the agent to ignore embedded commands within the ingested data.
  • Capability inventory: None; the skill is limited to text generation and does not utilize any tools for shell access, network operations, or file system modifications.
  • Sanitization: Absent; the ingested data is processed directly to extract stylistic patterns without validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:52 PM
Security Audit — agent-trust-hub — ghost-writer