style-extract

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes articles provided by users to perform stylistic analysis, which is a potential vector for indirect prompt injection if the source text contains malicious instructions.\n
  • Ingestion points: Articles and prose text provided by the user for analysis in 'Mode A' as described in SKILL.md.\n
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' directives to isolate the data being analyzed from the agent's instructions.\n
  • Capability inventory: The skill instructs the agent to create directories and write or append data to JSON and JSONL files within the './writing-workspace/styles/' directory.\n
  • Sanitization: The instructions recommend character escaping for JSON integrity but do not include content-based filtering or sanitization to prevent the agent from interpreting instructions within the analyzed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 07:38 PM