format-script-to-style

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it transforms untrusted script content provided by the calling agent's conversation context.
  • Ingestion points: Script content is ingested from the calling agent's conversation context as described in the Workflow section of SKILL.md.
  • Boundary markers: Absent; no delimiters or 'ignore instructions' warnings are specified for the input script content.
  • Capability inventory: The skill involves rewriting text based on templates and generating metadata comments for subsequent tools.
  • Sanitization: Absent; there is no evidence of sanitization or escaping of the input content before it is processed by the agent.
  • [DATA_EXFILTRATION]: The skill uses a hardcoded absolute file path (/Users/0xhbam/Desktop/Cursor/content-goose/DELIVERY_STYLES.md) to load its delivery style configuration. This exposes local system metadata, specifically the host's username ('0xhbam') and internal directory hierarchy, to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:39 PM
Security Audit — agent-trust-hub — format-script-to-style