outline-writer
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates within expected parameters for a content generation tool, reading user-provided source files and writing structured output to a designated directory. It follows a transparent step-by-step process with user checkpoints.- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its core function of processing external data from user-provided files (.md, .txt, .pdf). Without explicit boundary markers, malicious instructions inside these files could potentially influence agent behavior. * Ingestion points: User-provided content ingested in Step 1. * Boundary markers: Absent; the skill does not wrap source content in protective delimiters. * Capability inventory: WebSearch and file read/write operations. * Sanitization: Absent; the skill does not filter or sanitize the content of the source documents before analysis.
Audit Metadata